Model catalog

37 curated open-weight models. Click any model to see what runs on your rig.

DeepSeek-R1 (distill) 1.5B · 7B · 8B (Llama) · 14B · 32B · 70B (Llama)
Open reasoning model. Distilled into Qwen/Llama backbones you can actually run locally.
reasoningcodinggeneral
Llama 3.1 8B · 70B
Meta's workhorse general model. Reliable all-rounder with 128K context.
chatgeneralreasoningagents
Qwen2.5 0.5B · 1.5B · 3B · 7B · 14B · 32B · 72B
Alibaba's strong multilingual family across every size from 0.5B to 72B.
chatgeneralreasoningagents
Qwen2.5-Coder 1.5B · 7B · 14B · 32B
Best open coding model class. The 32B rivals proprietary coders; 7B/14B fit most rigs.
codingagents
Qwen3 1.7B · 4B · 8B · 14B · 32B · 30B-A3B (MoE)
Latest Qwen generation with hybrid thinking modes. Strong reasoning per parameter.
chatgeneralreasoningagentscoding
Gemma 4 12B
Google's Gemma 3 successor: unified any-to-any with vision, 256K context, Apache-2.0.
chatgeneralvision
Llama 3.2 1B · 3B
Tiny Llamas for edge + on-device. Fast, light, 128K context.
chatgeneralagents
Llama 3.3 70B
70B that rivals far larger models. The best open general model that fits a 64GB Mac.
chatgeneralreasoningagents
Mistral 7B 7B
The classic fast 7B. Apache-licensed, runs anywhere.
chatgeneralagents
Mistral Small 3 24B
24B that punches at 70B level with much faster generation. 32K context.
chatgeneralreasoningagents
Gemma 3 1B · 4B · 12B · 27B
Google's latest, with vision and 128K context. Strong quality per parameter.
chatgeneralvision
Mistral Nemo 12B
12B with 128K context, built with NVIDIA. Great mid-size all-rounder.
chatgeneralagents
Gemma 2 2B · 9B · 27B
Google's efficient open models. The 9B is a standout for its size. 8K context.
chatgeneral
Phi-4 14B
Microsoft's 14B that reasons above its weight, especially at math. 16K context.
reasoninggeneralcoding
Nomic Embed Text 137M
Fast, high-quality text embeddings for RAG. Tiny — runs anywhere.
embeddingsrag
Mixtral 8x7B 8x7B (MoE)
Sparse MoE: 47B total but only ~13B active per token, so it decodes fast — if it fits in memory.
chatgeneralreasoning
Codestral 22B
Mistral's 22B code model with strong fill-in-the-middle. 32K context.
codingagents
Phi-4-mini 3.8B
3.8B with 128K context — a capable little reasoner for light rigs.
reasoninggeneralchat
Llama 3.2 Vision 11B
Multimodal Llama — image understanding plus chat. 11B fits a 16GB+ Mac.
visionchat
mxbai-embed-large 335M
Strong open embedding model for retrieval. Small and quick.
embeddingsrag
Phi-3.5-mini 3.8B
3.8B with 128K context. No GQA, so KV grows fast at long context.
generalchatreasoning
SmolLM2 1.7B
Tiny but surprisingly capable. Runs on almost anything, even CPU.
chatgeneral
StarCoder2 3B · 7B · 15B
BigCode's permissive code models trained on The Stack v2.
coding
Code Llama 7B · 13B · 34B
Meta's Llama-2-based code models. Still popular on Ollama for completion.
coding
Yi 1.5 6B · 9B · 34B
01.AI's bilingual models, strong at reasoning and code for their size.
chatgeneralreasoning
Command R 35B
Cohere's RAG/tool-use specialist. No GQA, so KV cache is heavy at long context.
ragagentsgeneral
LLaVA 7B · 13B
Popular open vision-language model for image Q&A and captioning.
visionchat
TinyLlama 1.1B
1.1B — the classic 'will it run on a potato' model. Yes, it will.
chatgeneral
Granite 3.1 8B 8B
chatcodingreasoningrag
Falcon3 7B 7B
chatcodingreasoning
OLMo 2 7B 7B
chatgeneral
Yi-Coder 9B 9B
coding
Nemotron-Mini 4B 4B
chatreasoning
QwQ 32B 32B
reasoningchat
Qwen3 Coder 30B-A3B 30B-A3B (MoE)
codingagents
Granite 3.3 8B 8B
chatragagents
SmolLM3 3B 3B
chatgeneralreasoning