Open-Source LLMs logopeterindia.net
Knowledge Hub

Open-weight & Open-source Large Language Models

A directory of open-weight and open-source large language models — frontier-scale models, small and efficient families, and the tools used to run them locally.

22 topics•4 categories•Updated October 2026

Frontier-scale Open-weight Models

7 entries

Large models with published weights.

01DeepSeek-V3.2Reasoning-first models built for agents. Now available on web, app, and API — with state-of-the-art performance on complex multi-step tasks. 02Qwen3-235B-A22BPacks 235B total parameters (22B active per token across 128 experts) and delivers state-of-the-art performance on instruction following, coding, math, and science benchmarks. 03Kimi-K2.5A trillion-parameter MoE model (32B active parameters) that integrates vision natively from pretraining — trained on ~15 trillion mixed vision and text tokens with a constant vision-text mixing ratio throughout. 04GPT-OSS-120BAn open-weight model that fits into a single H100 GPU — 117B total parameters with only 5.1B active parameters per forward pass, enabling efficient large-scale inference. 05GLM-4.7-FlashThe strongest model in the 30B class — offers a new option for lightweight deployment that balances performance and efficiency for resource-constrained environments. 06MiMo-V2-FlashA powerful, efficient, and ultra-fast foundation language model that particularly excels in reasoning, coding, and agentic scenarios. 07Llama 4 (Scout & Maverick)Meta's Llama 4 series introduces natively multimodal models capable of processing both text and images from the ground up — not bolted on as an afterthought.

Other Open Model Families

5 entries

Established open and open-weight families.

08Meta Llama on Hugging FaceMeta's open-weight Llama family. 09Mistral AIEuropean lab with open and commercial models. 10IBM GraniteIBM's open models for business use. 11Olmo (Ai2)Ai2's fully open language model. 12SmolLM (Hugging Face)Hugging Face's small, fully open language models.

Run Models Locally

3 entries

Tools for running open models on your own hardware.

13OllamaRun open models locally with a simple command-line interface. 14llama.cppC/C++ inference engine for LLMs on CPUs and GPUs. 15LM StudioDesktop app for discovering and running local models.

Related Pages

7 entries

Related directories on this site.

16Large Language ModelsFrontier, open-weight and earlier models. 17Small Language ModelsCompact on-device models. 18LLM Model Formats ExplainedGGUF, GPTQ, AWQ and EXL2. 19LLMOpsOperating LLM applications. 20Language ModelsLanguage model architectures and types. 21Generative AIGenerative AI hub. 22State Space Models (SSMs) like MambaMamba, S4, hybrids such as Jamba, RWKV and other linear-time sequence models.

Frequently Asked Questions

What does open-weight mean?

The trained model weights are published so you can download, run and often fine-tune the model, though licences differ and training data and code may not be released.

How is open-weight different from open-source?

Open-source in the strict sense includes licence freedom and open training code and data; many popular models are open-weight with custom licences.

Can I run these models locally?

Smaller models run on laptops using Ollama, llama.cpp or LM Studio; the largest need multi-GPU servers.

What format should I download?

GGUF for CPU and edge, GPTQ, AWQ or EXL2 for GPUs; see the LLM Model Formats Explained page.

How do I check licences?

Read the model card and licence terms on each project page before commercial use.