Long context
Best long-context local LLMs
Models with unusually large context windows for documents and repos.
36 models in this collection.
Gemma 4 26B A4B
Gemma · 26B
Gemma 4 31B
Gemma · 31B
Command R 35B
Command · 35B
Command R+ 104B
Command · 104B
DeepSeek Coder V2 Lite 16B
DeepSeek · 16B
DeepSeek R1 671B
DeepSeek · 671B
DeepSeek R1 Distill Llama 70B
DeepSeek · 70B
Best for Enterprise-grade local pilots
DeepSeek R1 Distill Llama 8B
DeepSeek · 8B
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · 1.5B
DeepSeek R1 Distill Qwen 14B
DeepSeek · 14B
Best for Reasoning-intensive workflows
DeepSeek R1 Distill Qwen 32B
DeepSeek · 32B
Best for High-value reasoning tasks
DeepSeek R1 Distill Qwen 7B
DeepSeek · 7B
Best for Reasoning tasks
DeepSeek V3 671B
DeepSeek · 671B
Gemma 4 E2B
Gemma · 2.3B
Gemma 4 E4B
Gemma · 4.5B
Best for On-device multimodal assistants
Hermes 3 Llama 3.1 70B
Hermes · 70B
Hermes 3 Llama 3.1 8B
Hermes · 8B
Llama 3.1 405B
Llama · 405B
Llama 3.1 70B
Llama · 70B
Llama 3.1 8B
Llama · 8B
Best for General use
Llama 3.1 Nemotron 70B
Nemotron · 70B
Llama 3.2 1B
Llama · 1.24B
Llama 3.2 3B
Llama · 3.21B
Llama 3.3 70B
Llama · 70B
Best for High-end workstations
Llama 4 Maverick 17B (128E)
Llama · 17B
Llama 4 Scout 17B (16E)
Llama · 17B
Best for Mid/high-end hardware
Mistral Nemo 12B
Mistral · 12B
Best for Multilingual assistants
Mistral Small 3.1 24B
Mistral · 24B
Qwen 2.5 1.5B
Qwen · 1.5B
Qwen 2.5 14B
Qwen · 14B
Best for Internal team assistants
Qwen 2.5 32B
Qwen · 32B
Best for High-end local deployments
Qwen 2.5 3B
Qwen · 3B
Qwen 2.5 72B
Qwen · 72B
Qwen 2.5 7B
Qwen · 7B
Best for General multilingual assistants
Qwen 2.5 Coder 32B
Qwen · 32B
QwQ 32B
Qwen · 32B
Best for Expert analytical users