ModelVaultAI Index
All ModelsLocal RunCloud APIs
AI Cost CalculatorLive
Token CalculatorSoon
Context CalculatorSoon
VRAM CalculatorSoon
Admin PanelDashboardCompare
Compare
Category Catalog

Text / Chat AI Models

General-purpose conversation, writing, translation, and summary models.

OpenAI
Paid API

GPT-4o

Omnimodal LLM

GPT-4o by OpenAI - Omnimodal LLM for enterprise and developer workflows.

Context Window128k
MMLU88.7
Cloud Only
#flagship#omni
OpenAI
Freemium

GPT-4o mini

Lightweight LLM

GPT-4o mini by OpenAI - Lightweight LLM for enterprise and developer workflows.

Context Window128k
MMLU82
Cloud Only
#mini#fast
OpenAI
Paid API

GPT-4 Turbo

Large Language Model

GPT-4 Turbo by OpenAI - Large Language Model for enterprise and developer workflows.

Context Window128k
MMLU86.5
Cloud Only
#gpt4#turbo
OpenAI
Paid API

GPT-4

Large Language Model

GPT-4 by OpenAI - Large Language Model for enterprise and developer workflows.

Context Window8k
MMLU86.4
Cloud Only
#gpt4#legacy
OpenAI
Paid API

GPT-3.5 Turbo

Lightweight LLM

GPT-3.5 Turbo by OpenAI - Lightweight LLM for enterprise and developer workflows.

Context Window16k
MMLU70
Cloud Only
#gpt3.5
Anthropic
Paid API

Claude 3.5 Sonnet

Frontier LLM

Claude 3.5 Sonnet by Anthropic - Frontier LLM engineered for high safety, reasoning, and long context.

Context Window200k
SWE-bench49
Cloud Only
#claude#coding
Anthropic
Paid API

Claude 3.5 Haiku

Lightweight LLM

Claude 3.5 Haiku by Anthropic - Lightweight LLM engineered for high safety, reasoning, and long context.

Context Window200k
HumanEval88.1
Cloud Only
#claude#haiku
Anthropic
Paid API

Claude 3 Opus

Frontier LLM

Claude 3 Opus by Anthropic - Frontier LLM engineered for high safety, reasoning, and long context.

Context Window200k
MMLU86.8
Cloud Only
#claude#opus
Anthropic
Paid API

Claude 3 Sonnet

Enterprise LLM

Claude 3 Sonnet by Anthropic - Enterprise LLM engineered for high safety, reasoning, and long context.

Context Window200k
MMLU79
Cloud Only
#claude#sonnet
Anthropic
Paid API

Claude 3 Haiku

Lightweight LLM

Claude 3 Haiku by Anthropic - Lightweight LLM engineered for high safety, reasoning, and long context.

Context Window200k
MMLU75.2
Cloud Only
#claude#haiku
Anthropic
Paid API

Claude 2.1

Enterprise LLM

Claude 2.1 by Anthropic - Enterprise LLM engineered for high safety, reasoning, and long context.

Context Window200k
MMLU78.5
Cloud Only
#claude2
Anthropic
Paid API

Claude 2.0

Large LLM

Claude 2.0 by Anthropic - Large LLM engineered for high safety, reasoning, and long context.

Context Window100k
MMLU76.5
Cloud Only
#claude2
Anthropic
Paid API

Claude Instant 1.2

Lightweight LLM

Claude Instant 1.2 by Anthropic - Lightweight LLM engineered for high safety, reasoning, and long context.

Context Window100k
MMLU72
Cloud Only
#instant
Google AI
Freemium

Gemini 2.0 Flash

Omnimodal LLM

Gemini 2.0 Flash - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU75
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 2.0 Flash-Lite

Omnimodal LLM

Gemini 2.0 Flash-Lite - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU76
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 2.0 Pro

Omnimodal LLM

Gemini 2.0 Pro - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU77
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 2.0 Flash Thinking

Omnimodal LLM

Gemini 2.0 Flash Thinking - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU78
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 1.5 Pro

Omnimodal LLM

Gemini 1.5 Pro - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU79
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 1.5 Flash

Omnimodal LLM

Gemini 1.5 Flash - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU80
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 1.5 Flash-8B

Omnimodal LLM

Gemini 1.5 Flash-8B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window1M
MMLU81
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 1.0 Pro

Omnimodal LLM

Gemini 1.0 Pro - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU82
Cloud Only
#google#gemini
Google AI
Freemium

Gemini 1.0 Ultra

Omnimodal LLM

Gemini 1.0 Ultra - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU83
Cloud Only
#google#gemini
Google AI
Open Weights

Gemma 2 27B

Open Weights LLM

Gemma 2 27B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU84
Cloud API Local Run
#google#gemini
Google AI
Open Weights

Gemma 2 9B

Open Weights LLM

Gemma 2 9B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU85
Cloud API Local Run
#google#gemini
Google AI
Open Weights

Gemma 2 2B

Open Weights LLM

Gemma 2 2B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU86
Cloud API Local Run
#google#gemini
Google AI
Open Weights

Gemma 7B

Open Weights LLM

Gemma 7B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU87
Cloud API Local Run
#google#gemini
Google AI
Open Weights

Gemma 2B

Open Weights LLM

Gemma 2B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU88
Cloud API Local Run
#google#gemini
Google AI
Open Weights

CodeGemma 7B

Open Weights LLM

CodeGemma 7B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU89
Cloud API Local Run
#google#gemini
Google AI
Open Weights

CodeGemma 2B

Open Weights LLM

CodeGemma 2B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU75
Cloud API Local Run
#google#gemini
Google AI
Open Weights

RecurrentGemma 2B

Open Weights LLM

RecurrentGemma 2B - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU76
Cloud API Local Run
#google#gemini
Google AI
Freemium

MusicLM

Omnimodal LLM

MusicLM - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU81
Cloud Only
#google#gemini
Google AI
Freemium

AudioLM

Omnimodal LLM

AudioLM - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU82
Cloud Only
#google#gemini
Google AI
Freemium

PaLM 2

Omnimodal LLM

PaLM 2 - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU83
Cloud Only
#google#gemini
Google AI
Freemium

PaLM 2 Bison

Omnimodal LLM

PaLM 2 Bison - Google AI multimodal model designed for high throughput, reasoning, and synthesis.

Context Window128k
MMLU84
Cloud Only
#google#gemini
Meta AI
Open Weights

Llama 3.3 70B

Open Weights LLM

Llama 3.3 70B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU65
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3.2 3B

Open Weights LLM

Llama 3.2 3B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU68
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3.2 1B

Open Weights LLM

Llama 3.2 1B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU69
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3.1 405B

Open Weights LLM

Llama 3.1 405B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU70
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3.1 70B

Open Weights LLM

Llama 3.1 70B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU71
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3.1 8B

Open Weights LLM

Llama 3.1 8B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU72
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3 70B

Open Weights LLM

Llama 3 70B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU73
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 3 8B

Open Weights LLM

Llama 3 8B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU74
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 2 70B

Open Weights LLM

Llama 2 70B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU75
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 2 13B

Open Weights LLM

Llama 2 13B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU76
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama 2 7B

Open Weights LLM

Llama 2 7B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU77
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama Guard 3 8B

Open Weights LLM

Llama Guard 3 8B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU82
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Llama Guard 3 1B

Open Weights LLM

Llama Guard 3 1B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU83
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Prompt Guard 86M

Open Weights LLM

Prompt Guard 86M - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU84
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Segment Anything 2 (SAM 2)

Vision LLM

Segment Anything 2 (SAM 2) - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU85
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

SAM 1

Vision LLM

SAM 1 - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU86
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

SeamlessM4T v2

Open Weights LLM

SeamlessM4T v2 - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU87
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Seamless Expressive

Open Weights LLM

Seamless Expressive - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU88
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

Bark

Open Weights LLM

Bark - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU66
Cloud API Local Run
#meta#llama
Meta AI
Open Weights

MovieGen

Open Weights LLM

MovieGen - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Context Window128k
MMLU68
Cloud API Local Run
#meta#llama
Mistral AI
Open Weights

Mistral Large 2

Open Weights LLM

Mistral Large 2 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU70
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral Large

Open Weights LLM

Mistral Large - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU71
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral Medium

Open Weights LLM

Mistral Medium - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU72
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral Small 3

Open Weights LLM

Mistral Small 3 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU73
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral Small 2

Open Weights LLM

Mistral Small 2 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU74
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral NeMo 12B

Open Weights LLM

Mistral NeMo 12B - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU75
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral 7B v0.3

Open Weights LLM

Mistral 7B v0.3 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU76
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral 7B v0.2

Open Weights LLM

Mistral 7B v0.2 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU77
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral 7B v0.1

Open Weights LLM

Mistral 7B v0.1 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU78
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mixtral 8x22B

MoE LLM

Mixtral 8x22B - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU83
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mixtral 8x7B

MoE LLM

Mixtral 8x7B - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU84
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mathstral 7B

Open Weights LLM

Mathstral 7B - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU85
Cloud API Local Run
#mistral#open-weights
Mistral AI
Open Weights

Mistral Embed 2

Open Weights LLM

Mistral Embed 2 - European frontier open & commercial model by Mistral AI.

Context Window128k
MMLU86
Cloud API Local Run
#mistral#open-weights
DeepSeek
Open Weights

DeepSeek-V3

MoE LLM

DeepSeek-V3 - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code82
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

DeepSeek-V2.5

MoE LLM

DeepSeek-V2.5 - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code83
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

DeepSeek-V2

MoE LLM

DeepSeek-V2 - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code84
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

DeepSeek Math 7B

MoE LLM

DeepSeek Math 7B - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code90
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

DeepSeek VL2

Vision LLM

DeepSeek VL2 - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code91
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

DeepSeek VL 7B

Vision LLM

DeepSeek VL 7B - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code92
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

Janus Pro 7B

Vision LLM

Janus Pro 7B - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code81
Cloud API Local Run
#deepseek#mit-license
DeepSeek
Open Weights

Janus 1.3B

Vision LLM

Janus 1.3B - DeepSeek open-source frontier model for math, reasoning, and code.

Context Window128k
MATH / Code82
Cloud API Local Run
#deepseek#mit-license
Alibaba Cloud
Open Weights

Qwen 2.5 72B

Open Weights LLM

Qwen 2.5 72B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval72
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 32B

Open Weights LLM

Qwen 2.5 32B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval73
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 14B

Open Weights LLM

Qwen 2.5 14B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval74
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 7B

Open Weights LLM

Qwen 2.5 7B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval75
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 3B

Open Weights LLM

Qwen 2.5 3B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval76
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 1.5B

Open Weights LLM

Qwen 2.5 1.5B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval77
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 0.5B

Open Weights LLM

Qwen 2.5 0.5B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval78
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 Math 72B

Math Model

Qwen 2.5 Math 72B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval85
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2.5 Math 7B

Math Model

Qwen 2.5 Math 7B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval86
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2 72B

Open Weights LLM

Qwen 2 72B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval90
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 2 57B A14B

Open Weights LLM

Qwen 2 57B A14B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval91
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 1.5 110B

Open Weights LLM

Qwen 1.5 110B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval92
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen 1.5 72B

Open Weights LLM

Qwen 1.5 72B - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval93
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

QPad

Open Weights LLM

QPad - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval72
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen-Audio

Open Weights LLM

Qwen-Audio - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval73
Cloud API Local Run
#qwen#alibaba
Alibaba Cloud
Open Weights

Qwen-Agent

Open Weights LLM

Qwen-Agent - Alibaba Qwen open multilingual model series.

Context Window128k
MMLU / HumanEval74
Cloud API Local Run
#qwen#alibaba
Hugging Face
Open Weights

SmolLM2 1.7B

Open Weights LLM

SmolLM2 1.7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU60
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

SmolLM2 360M

Open Weights LLM

SmolLM2 360M - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU61
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

SmolLM2 135M

Open Weights LLM

SmolLM2 135M - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU62
Cloud API Local Run
#huggingface#open-source
IBM
Open Weights

Granite 3.1 8B

Open Weights LLM

Granite 3.1 8B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU63
Cloud API Local Run
#huggingface#open-source
IBM
Open Weights

Granite 3.1 2B

Open Weights LLM

Granite 3.1 2B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU64
Cloud API Local Run
#huggingface#open-source
IBM
Open Weights

Granite 3.0 8B

Open Weights LLM

Granite 3.0 8B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU65
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-4 14B

Open Weights LLM

Phi-4 14B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU67
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-3.5 Mini

Open Weights LLM

Phi-3.5 Mini - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU69
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-3.5 MoE

Open Weights LLM

Phi-3.5 MoE - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU70
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-3 Medium

Open Weights LLM

Phi-3 Medium - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU71
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-3 Small

Open Weights LLM

Phi-3 Small - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU72
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-3 Mini

Open Weights LLM

Phi-3 Mini - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU73
Cloud API Local Run
#huggingface#open-source
Microsoft
Open Weights

Phi-2

Open Weights LLM

Phi-2 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU74
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Instructor Large

Open Weights LLM

Instructor Large - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU83
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

All-mpnet-base-v2

Open Weights LLM

All-mpnet-base-v2 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU85
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Longformer

Open Weights LLM

Longformer - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU65
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

BigBird

Open Weights LLM

BigBird - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU66
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

TrOCR

Open Weights LLM

TrOCR - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU69
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

EasyOCR

Open Weights LLM

EasyOCR - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU70
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

MiniCPM-V 2.6

Open Weights LLM

MiniCPM-V 2.6 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU72
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

MiniCPM 3 4B

Open Weights LLM

MiniCPM 3 4B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU73
Cloud API Local Run
#huggingface#open-source
01.AI
Open Weights

Yi 1.5 34B

Open Weights LLM

Yi 1.5 34B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU78
Cloud API Local Run
#huggingface#open-source
01.AI
Open Weights

Yi 1.5 9B

Open Weights LLM

Yi 1.5 9B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU79
Cloud API Local Run
#huggingface#open-source
01.AI
Open Weights

Yi 1.5 6B

Open Weights LLM

Yi 1.5 6B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU80
Cloud API Local Run
#huggingface#open-source
01.AI
Open Weights

Yi Lightning

Open Weights LLM

Yi Lightning - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU81
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

ERNIE 4.0 Turbo

Open Weights LLM

ERNIE 4.0 Turbo - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU82
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

ERNIE 3.5

Open Weights LLM

ERNIE 3.5 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU83
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Tencent Hunyuan

Open Weights LLM

Tencent Hunyuan - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU84
Cloud API Local Run
#huggingface#open-source
Zhipu AI
Open Weights

GLM-4 9B

Open Weights LLM

GLM-4 9B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU85
Cloud API Local Run
#huggingface#open-source
Zhipu AI
Open Weights

GLM-4V 9B

Open Weights LLM

GLM-4V 9B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU86
Cloud API Local Run
#huggingface#open-source
Zhipu AI
Open Weights

GLM-4 Flash

Open Weights LLM

GLM-4 Flash - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU87
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Baichuan 2 13B

Open Weights LLM

Baichuan 2 13B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU88
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

InternLM 2.5 20B

Open Weights LLM

InternLM 2.5 20B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU89
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

InternLM 2.5 7B

Open Weights LLM

InternLM 2.5 7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU60
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Reka Flash

Open Weights LLM

Reka Flash - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU63
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Reka Core

Open Weights LLM

Reka Core - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU64
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Reka Edge

Open Weights LLM

Reka Edge - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU65
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

DBRX Instruct

Open Weights LLM

DBRX Instruct - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU66
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Snowflake Arctic 480B

Open Weights LLM

Snowflake Arctic 480B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU67
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

DeciLM 7B

Open Weights LLM

DeciLM 7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU68
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

RWKV 6 7B

Open Weights LLM

RWKV 6 7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU69
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Mamba 2.8B

Open Weights LLM

Mamba 2.8B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU70
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Jamba 1.5 Large

Open Weights LLM

Jamba 1.5 Large - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU71
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Jamba 1.5 Mini

Open Weights LLM

Jamba 1.5 Mini - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU72
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Jurassic 2 Ultra

Open Weights LLM

Jurassic 2 Ultra - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU73
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Solar 10.7B

Open Weights LLM

Solar 10.7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU74
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Solar Pro 22B

Open Weights LLM

Solar Pro 22B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU75
Cloud API Local Run
#huggingface#open-source
TII Falcon
Open Weights

Falcon 2 11B

Open Weights LLM

Falcon 2 11B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU76
Cloud API Local Run
#huggingface#open-source
TII Falcon
Open Weights

Falcon 180B

Open Weights LLM

Falcon 180B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU77
Cloud API Local Run
#huggingface#open-source
TII Falcon
Open Weights

Falcon 40B

Open Weights LLM

Falcon 40B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU78
Cloud API Local Run
#huggingface#open-source
TII Falcon
Open Weights

Falcon 7B

Open Weights LLM

Falcon 7B - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU79
Cloud API Local Run
#huggingface#open-source
Cohere
Open Weights

Command R+

Open Weights LLM

Command R+ - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU80
Cloud API Local Run
#huggingface#open-source
Cohere
Open Weights

Command R

Open Weights LLM

Command R - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU81
Cloud API Local Run
#huggingface#open-source
Cohere
Open Weights

Cohere Aya 23

Open Weights LLM

Cohere Aya 23 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU83
Cloud API Local Run
#huggingface#open-source
Hugging Face
Open Weights

Aya 101

Open Weights LLM

Aya 101 - Open-source benchmarked model available on Hugging Face Hub.

Context Window8k-32k
MMLU84
Cloud API Local Run
#huggingface#open-source
Meta AI / Community
Open Weights

Llama-3.1-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Llama-3.1-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score80
Local Model
#medical#ollama
Alibaba / Community
Open Weights

Qwen-2.5-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Qwen-2.5-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score81
Local Model
#medical#ollama
DeepSeek / Community
Open Weights

DeepSeek-V3-Medical-GGUF-Q4_K_M

Specialized Domain LLM

DeepSeek-V3-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score82
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Mistral-7B-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Mistral-7B-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score83
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Gemma-2-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Gemma-2-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score84
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Phi-3.5-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Phi-3.5-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score85
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Granite-3.1-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Granite-3.1-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score86
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Yi-1.5-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Yi-1.5-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score87
Local Model
#medical#ollama
Hugging Face Community
Open Weights

Falcon-2-Medical-GGUF-Q4_K_M

Specialized Domain LLM

Falcon-2-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score88
Local Model
#medical#ollama
Hugging Face Community
Open Weights

BGE-M3-Medical-GGUF-Q4_K_M

Specialized Domain LLM

BGE-M3-Medical-GGUF-Q4_K_M - Fine-tuned and quantized Medical domain model variant optimized for fast local host inference.

Context Window32k-128k
Medical Domain Score89
Local Model
#medical#ollama
ModelVault

The open directory for discovering, comparing, and benchmarking cloud and local AI models. Built for engineers, researchers, and technical leaders.

All 520+ Model Specifications Active
ProductAll AI Models IndexComparison MatrixLocal Models (Ollama)Cloud API ModelsAI Cost Calculator
ResourcesReasoning ModelsCoding AgentsVision-LanguageEmbeddings & RAG
Management & LegalAdmin Console ↗Privacy PolicyTerms of ServiceDisclaimerAbout ModelVaultContact Us
© 2025 ModelVault AI Directory. All model specifications verified.
Built for high-performance AI workflows