Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Local model runtimes
Run open-weight language models on your own hardware, behind a local API.
Changements dans cette catégorie (RSS)
Côte à côte
| Outil | Étoiles | Licence | Conditions | Auto-hébergeable | Langage | Dernière release | Dernier push |
|---|---|---|---|---|---|---|---|
| Ollama | 182k | MIT | Open source | Oui | Go | v0.35.1 | 2026-10-06 |
| llama.cpp | 130k | MIT | Open source | Oui | C++ | v0.6.0 | 2026-10-06 |
| vLLM | 93k | Apache-2.0 | Open source | Oui | Python | v0.31.0 | 2026-10-06 |
| LocalAI | 49k | MIT | Open source | Oui | Go | v4.11.0 | 2026-10-06 |
| exo | 48k | Apache-2.0 | Open source | Oui | Python | v1.0.71 | 2026-10-06 |
| SGLang | 37k | Apache-2.0 | Open source | Oui | Python | v0.5.21 | 2026-10-06 |
| llamafile | 26k | Other | Open source | Oui | C++ | 0.10.6 | 2026-10-06 |
| MLC LLM | 23k | Apache-2.0 | Open source | Oui | Python | v0.20.0 | 2026-10-04 |
| KTransformers | 20k | Apache-2.0 | Open source | Oui | Python | v0.7.1 | 2026-10-01 |
| TensorRT-LLM | 15k | Other | Open source | Oui | Python | v1.2.1 | 2026-10-06 |
| Xinference | 9.6k | Apache-2.0 | Open source | Oui | Python | v3.5.0 | 2026-10-06 |
| LMDeploy | 8.1k | Apache-2.0 | Open source | Oui | Python | v0.18.0 | 2026-09-28 |
| mistral.rs | 7.7k | MIT | Open source | Oui | Rust | v0.9.4 | 2026-10-01 |
| llama-swap | 5.9k | MIT | Open source | Oui | Go | v262 | 2026-10-05 |
| Lemonade | 5.8k | Apache-2.0 | Open source | Oui | C++ | v2026.40.0 | 2026-10-06 |
| GPUStack | 5.8k | Apache-2.0 | Open source | Oui | Python | v2.2.3 | 2026-09-30 |
| RamaLama | 3.1k | MIT | Open source | Oui | Python | v0.25.0 | 2026-10-05 |
| TabbyAPI | 1.5k | AGPL-3.0 | Open source | Oui | Python | aucune | 2026-10-06 |
18 outils
LLM inference in C/C++
A high-throughput and memory-efficient inference and serving engine for LLMs
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 93k
- Dernière release
- v0.31.0
- Dernier push
- 2026-10-06
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Run frontier AI locally.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 48k
- Dernière release
- v1.0.71
- Dernier push
- 2026-10-06
SGLang is a high-performance serving framework for large language models and multimodal models.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 37k
- Dernière release
- v0.5.21
- Dernier push
- 2026-10-06
Distribute and run LLMs with a single file.
Universal LLM Deployment Engine with ML Compilation
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 23k
- Dernière release
- v0.20.0
- Dernier push
- 2026-10-04
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 20k
- Dernière release
- v0.7.1
- Dernier push
- 2026-10-01
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 9.6k
- Dernière release
- v3.5.0
- Dernier push
- 2026-10-06
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 8.1k
- Dernière release
- v0.18.0
- Dernier push
- 2026-09-28
Fast, flexible LLM inference
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
- Langage
- C++
- Licence
- Apache-2.0
- Étoiles
- 5.8k
- Dernière release
- v2026.40.0
- Dernier push
- 2026-10-06
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
- Langage
- Python
- Licence
- Apache-2.0
- Étoiles
- 5.8k
- Dernière release
- v2.2.3
- Dernier push
- 2026-09-30
RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
The official API server for Exllama. OAI compatible, lightweight, and fast.