OSAIM
Open Source AI Models

55 open-source models indexed

The open-source AI model directory.

Licenses, parameters, benchmarks, VRAM and inference pricing for Llama, Mistral, Qwen, DeepSeek, Gemma, Phi and more. Pick the right open-weights model for your use case.

Partner spotlight
✨ Vincony — AI & web dev shop that ships production

Need a partner to build your open-source AI project, directory site or bespoke agent stack? Vincony builds sites like this one — Next 16, TypeScript, Supabase, Coolify — end to end.

Visit vincony.com →

Best models for…

All use cases →

Curated picks for the six workloads we get asked about most.

Featured models

See all →
Kimi K2 Instruct
1000B

Moonshot AI's 1-trillion-parameter mixture-of-experts (32B active per token). Trained on 15.5T tokens with a heavy emphasis on tool-use and agentic behaviour. Modified-MIT licence with an attribution clause for very-large deployments. Exceptional at long-horizon agent tasks; benchmarked well against Claude Sonnet on SWE-bench Verified.

Context
128K
License
kimi
VRAM Q4
600 GB
DeepSeek V3
671B

671B-parameter MoE model with 37B active per token. Trained for roughly $5.6M of compute — a landmark in cost-efficient frontier training. Frontier-class quality at a fraction of the cost of the closed proprietary frontier. The DeepSeek licence permits commercial use with limited restrictions on military and unlawful applications. Running V3 yourself requires serious hardware (8× H100 at fp8); most teams will use it via the DeepSeek API or providers like Together.

Context
128K
License
deepseek
VRAM Q4
402.6 GB
DeepSeek R1
671B

Reasoning model trained with reinforcement learning on top of DeepSeek V3-Base. MIT licence — even the weights are unrestricted, making R1 the most permissively-licensed frontier reasoning model. Generates long internal chains-of-thought before answering, trading latency for accuracy on math, code, and reasoning benchmarks. Distilled variants (e.g. R1 Distill Llama 70B) recover most of the quality at much smaller scales.

Context
128K
License
mit
VRAM Q4
402.6 GB
Llama 3.1 405B Instruct
405B

Meta's July 2024 flagship — the first open-weights model at 405B parameters. Trained on 15T tokens with 128K context. Rivals GPT-4o on many academic benchmarks and set the ceiling for open-weights quality for most of 2024. Running it self-hosted requires serious hardware (8× H100 at fp8 or multi-node at fp16); most users will run it via a hosted provider (Together, Groq, Fireworks). Llama 3.3 70B closed most of the practical gap at a fraction of the cost, so 405B is now most useful when 70B specifically hits its ceiling.

Context
128K
License
llama-3
VRAM Q4
243 GB
Jamba 1.5 Large
398B

Hybrid Mamba-Transformer-MoE model with native 256K context (effective beyond 140K). 94B active parameters out of 398B total. The state-space-model layers give it linear-time scaling with sequence length, making it interesting for very long contexts. Licensed under AI21's open model licence, which permits most commercial use.

Context
256K
License
jamba-open
VRAM Q4
238.8 GB
Nemotron-4 340B Instruct
340B

NVIDIA's reward-modelling research vehicle. Trained primarily to be a synthetic-data-generation specialist rather than a chat-first model. Useful for teams building instruction-tuning datasets at scale.

Context
4K
License
llama-3
VRAM Q4
204 GB

Browse by family

Command
Cohere

Cohere's enterprise-oriented model family. Command R+ targets retrieval-augmented generation workflows.

DBRX
Databricks

Databricks' 132B mixture-of-experts (12 of 16 experts active per token) built on the MegaBlocks stack. Released under the Databricks Open Model Licence.

DeepSeek
DeepSeek

Hangzhou-based lab known for highly efficient MoE training. DeepSeek V3 and R1 set new bars for open reasoning and coding.

Falcon
TII

Technology Innovation Institute (UAE). Falcon Mamba pioneered state-space-model open releases.

Gemma
Google DeepMind

Google's open-weights model family derived from the same research as Gemini. Strong performance at small scales.

Grok
xAI

xAI's open-weights releases. Grok 1 and Grok 2 weights have been published under Apache 2.0.

Hermes
NousResearch

Nous Research's community-driven fine-tune series. Hermes 3 sits on top of Llama 3.1 base weights, tuned for very strong tool use and steerable roleplay behaviour.

Jamba
AI21 Labs

Hybrid Mamba/Transformer architecture with very long native context windows.

Kimi
Moonshot AI

Beijing-based lab founded by ex-Tsinghua researchers. Kimi K1.5 and K2 push very long context and reasoning; K2 is a trillion-parameter MoE with strong tool-use behaviour.

Llama
Meta

Meta's open-weights LLM family. Llama 3 introduced 128K context and strong instruction tuning across 1B–405B parameter scales.

Mistral
Mistral AI

Paris-based lab whose dense and mixture-of-experts open-weights models popularised sliding-window attention and high efficiency.

Nemotron
NVIDIA

NVIDIA's research and instruction-tuning effort built on top of Llama base models, with strong RLHF and reward-modelling work.

OLMo
Allen Institute for AI

AI2's fully-open initiative: weights, data and training code all under permissive licences.

Phi
Microsoft

Microsoft's small-language-model line, focused on data-quality-driven training. Phi-4 punches well above its weight class.

Qwen
Alibaba

Alibaba's Qwen series. Qwen2.5 delivers competitive frontier-class performance across sizes from 0.5B to 72B with permissive licensing.

Stable LM
Stability AI

Stability AI's general-purpose text models.

Yi
01.AI

01.AI's bilingual (Chinese/English) open-weights series including vision variants.

Browse by task

Browse by size

MMLU leaderboard — top 5

Full leaderboards →
  1. 90.80
  2. 89.50
  3. 88.50
  4. 87.30
  5. 87.10

Why open-source models matter

Open-weights models let you run inference locally, fine-tune on private data, and avoid vendor lock-in. Open Source AI Models tracks every model with public weights so you can pick on facts, not marketing.