exllamav3
by turboderp-orgIn its repository's words: “An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs”
Facts from GitHub
- Licence
- MIT (MIT License), permissive, our reading
- Activity
- Last push 16 Nov 2026: pushed to in the last 90 days
- Latest release
- v1.6.713 Nov 2026
- Stars
- 1.8k
- Main language
- Python
- On GitHub since
- 6 Apr 2025
What it says it supports
- Loads
- EXL3
- Runs on
- Linux, Windows
- Hardware
- NVIDIA
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.
EXL3 81
Qwen/Qwen3-0.6B, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, Qwen/Qwen3-32B, Qwen/Qwen3-VL-4B-Instruct, Qwen/Qwen3.8-Flash-Next, mistralai/Mistral-7B-Instruct-v0.3, deepseek-ai/DeepSeek-V4-Flash-0731, zai-org/GLM-5.3, google/gemma-4-12B-it, deepseek-ai/DeepSeek-V4.1-Flash, Qwen/Qwen3.5-35B-A3B, and 69 more, most downloaded first
Other tools in Run locally
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.