inference
by xorbitsaiIn its repository's words: “Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.”
Facts from GitHub
- Licence
- Apache-2.0 (Apache License 2.0), permissive, our reading
- Activity
- Last push 19 Nov 2026: pushed to in the last 90 days
- Latest release
- not fetched yet
- Stars
- 9.7k
- Main language
- Python
- On GitHub since
- 14 Jun 2023
- Topics
- artificial-intelligence, diffusers, gemma, glm, glm-5-3, inference, kimi, kimi-k3, llama-cpp, llamacpp, llm, machine-learning, mlx, openai-api, pytorch, qwen, sglang, transformers, vllm, whisper
What it says it supports
- Loads
- safetensors, MLX
- Runs on
- Linux, macOS, Windows
- Hardware
- NVIDIA, Apple silicon, CPU only
Each item is on our list for this tool and named in its README. A mention is not a test: check the project's documentation for your setup.
Reviewed models it can load
Matched by file format only, from our snapshot of the Hub: GGUF where we measured GGUF files, other formats where a conversion exists, safetensors for the original weights. Support for a new architecture can lag behind its release.
safetensors 428
openai-community/gpt2, microsoft/Florence-2-base, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, and 416 more, most downloaded first
MLX 284
openai-community/gpt2, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, baidu/Unlimited-OCR, and 272 more, most downloaded first
Other tools in Serve
Tool data from the GitHub API, fetched 19 Nov 2026, 15:36 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.