Coding Agents AI Models

Omnimodal LLM

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

Lightweight LLM

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

Reasoning Model

OpenAI o3 by OpenAI - Reasoning Model for enterprise and developer workflows.

Reasoning Model

OpenAI o3-mini by OpenAI - Reasoning Model for enterprise and developer workflows.

Reasoning Model

OpenAI o1 by OpenAI - Reasoning Model for enterprise and developer workflows.

Lightweight Reasoning

OpenAI o1-mini by OpenAI - Lightweight Reasoning for enterprise and developer workflows.

Large Language Model

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

Frontier LLM

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

Lightweight LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Open Weights LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Omnimodal LLM

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

Code LLM

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

Code LLM

Code Llama 34B - Meta AI open source model engineered for high efficiency, vision, and edge performance.

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

Codestral 22B - European frontier open & commercial model by Mistral AI.

Code LLM

Codestral Mamba - European frontier open & commercial model by Mistral AI.

Code LLM

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

Code LLM

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

Code LLM

DeepSeek Coder 33B - DeepSeek open-source frontier model for math, reasoning, and code.

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

Granite Code 34B - Open-source benchmarked model available on Hugging Face Hub.

Code LLM

StarCoder 2 15B - Open-source benchmarked model available on Hugging Face Hub.

Code LLM

StarCoder 2 7B - Open-source benchmarked model available on Hugging Face Hub.

Code LLM

StarCoder 2 3B - Open-source benchmarked model available on Hugging Face Hub.

Code LLM

CodeGen 16B - Open-source benchmarked model available on Hugging Face Hub.

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

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

Code LLM

Llama-3.1-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-GGUF-Q8_0 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-AWQ-INT4 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-GPTQ-4bit - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-EXL2-5.0bpw - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-FP8-quant - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-FP16-full - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-Uncensored-Instruct - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-RAG-FineTune - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-Hermes-3 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-OpenChat-3.5 - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Llama-3.1-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Qwen-2.5-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

DeepSeek-V3-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Mistral-7B-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Gemma-2-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Phi-3.5-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Granite-3.1-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Yi-1.5-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

Falcon-2-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.

Code LLM

BGE-M3-Code-Nexus-Agent - Fine-tuned and quantized Code domain model variant optimized for fast local host inference.