Reasoning AI Models

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.

Frontier LLM

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

Reasoning Model

DeepSeek-R1 - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Zero - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Qwen-32B - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Qwen-14B - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Qwen-7B - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Qwen-1.5B - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Llama-70B - DeepSeek open-source frontier model for math, reasoning, and code.

Reasoning Model

DeepSeek-R1-Distill-Llama-8B - DeepSeek open-source frontier model for math, reasoning, and code.

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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

Math Model

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