← LLM Directory
Ollama
Hosted PlatformRun 100+ open-weight models locally. No API costs. The easiest way to self-host LLMs on Linux, macOS, and Windows.
Reasoning1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
DeepSeek R1 Open-weight reasoning model. Chain-of-thought included. | $0.000 | $0.000 | 131K |
Coding1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Codestral 22B Mistral's open-weight coding model. 80+ languages. | $0.000 | $0.000 | 66K |
RAG1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Command R Cohere's open-weight RAG model. Built for retrieval. | $0.000 | $0.000 | 131K |
Popular8 models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Qwen3 32B Best open-source 32B model. Great for local deployment. | $0.000 | $0.000 | 131K |
DeepSeek V3 671B MoE model. Top open-source general model. | $0.000 | $0.000 | 66K |
Llama 4 Maverick Meta's latest MoE. 128 active of 400B params. | $0.000 | $0.000 | 256K |
Llama 3.3 70B Stable workhorse 70B model for production. | $0.000 | $0.000 | 131K |
Gemma 3 27B Google's open-weight 27B. Strong for its size. | $0.000 | $0.000 | 128K |
Mistral Small 3.1 24B Mistral's latest small model. Vision support included. | $0.000 | $0.000 | 131K |
Phi-4 14B Microsoft's compact reasoning model. Punches above its weight. | $0.000 | $0.000 | 16K |
GLM-4 9B Zhipu AI's open-weight bilingual model. | $0.000 | $0.000 | 131K |
Featured3 models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Gemma 4 QAT 32B Google's latest. 72% less VRAM. Runs on 16GB GPUs. | $0.000 | $0.000 | 256K |
Gemma 4 QAT 14B Mid-size Gemma 4 QAT. Efficient for 8GB GPUs. | $0.000 | $0.000 | 128K |
Qwen3 235B-A22B MoE model. 22B active params. Strong coding and reasoning. | $0.000 | $0.000 | 131K |
Budget3 models
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Llama 3.1 8B Smallest Llama 3.1. Great for fine-tuning. | $0.000 | $0.000 | 131K |
Gemma 3 4B Compact Gemma for edge devices. | $0.000 | $0.000 | 131K |
Qwen3 4B Small Qwen for mobile and edge. | $0.000 | $0.000 | 33K |
Embedding1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Nomic Embed Text Open-weight embedding model for search and RAG. | $0.000 | $0.000 | 8K |
Image1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
Stable Diffusion 3.5 Open-weight image generation model. | $0.000 | $0.000 | — |
Edge1 model
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
SmolLM2 1.7B HuggingFace's tiny model. Runs on phones. | $0.000 | $0.000 | 8K |