← LLM Directory
Ollama

Ollama

Hosted Platform

Run 100+ open-weight models locally. No API costs. The easiest way to self-host LLMs on Linux, macOS, and Windows.

Reasoning1 model

ModelInput / 1MOutput / 1MContext
DeepSeek R1
Open-weight reasoning model. Chain-of-thought included.
$0.000$0.000131K

Coding1 model

ModelInput / 1MOutput / 1MContext
Codestral 22B
Mistral's open-weight coding model. 80+ languages.
$0.000$0.00066K

RAG1 model

ModelInput / 1MOutput / 1MContext
Command R
Cohere's open-weight RAG model. Built for retrieval.
$0.000$0.000131K

Popular8 models

ModelInput / 1MOutput / 1MContext
Qwen3 32B
Best open-source 32B model. Great for local deployment.
$0.000$0.000131K
DeepSeek V3
671B MoE model. Top open-source general model.
$0.000$0.00066K
Llama 4 Maverick
Meta's latest MoE. 128 active of 400B params.
$0.000$0.000256K
Llama 3.3 70B
Stable workhorse 70B model for production.
$0.000$0.000131K
Gemma 3 27B
Google's open-weight 27B. Strong for its size.
$0.000$0.000128K
Mistral Small 3.1 24B
Mistral's latest small model. Vision support included.
$0.000$0.000131K
Phi-4 14B
Microsoft's compact reasoning model. Punches above its weight.
$0.000$0.00016K
GLM-4 9B
Zhipu AI's open-weight bilingual model.
$0.000$0.000131K

Featured3 models

ModelInput / 1MOutput / 1MContext
Gemma 4 QAT 32B
Google's latest. 72% less VRAM. Runs on 16GB GPUs.
$0.000$0.000256K
Gemma 4 QAT 14B
Mid-size Gemma 4 QAT. Efficient for 8GB GPUs.
$0.000$0.000128K
Qwen3 235B-A22B
MoE model. 22B active params. Strong coding and reasoning.
$0.000$0.000131K

Budget3 models

ModelInput / 1MOutput / 1MContext
Llama 3.1 8B
Smallest Llama 3.1. Great for fine-tuning.
$0.000$0.000131K
Gemma 3 4B
Compact Gemma for edge devices.
$0.000$0.000131K
Qwen3 4B
Small Qwen for mobile and edge.
$0.000$0.00033K

Embedding1 model

ModelInput / 1MOutput / 1MContext
Nomic Embed Text
Open-weight embedding model for search and RAG.
$0.000$0.0008K

Image1 model

ModelInput / 1MOutput / 1MContext
Stable Diffusion 3.5
Open-weight image generation model.
$0.000$0.000

Edge1 model

ModelInput / 1MOutput / 1MContext
SmolLM2 1.7B
HuggingFace's tiny model. Runs on phones.
$0.000$0.0008K

Other Providers