Model-Optimizer
by NVIDIAIn its repository's words: “A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.”
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
- 5.6k
- Main language
- Python
- On GitHub since
- 23 Apr 2024
Other tools in Quantise and convert
- bitsandbytes bitsandbytes-foundation, 8.5k stars
- mergekit arcee-ai, 7.5k stars
- AutoGPTQ AutoGPTQ, 5.1k stars
- llm-compressor vllm-project, 4.0k stars
- llm-awq mit-han-lab, 3.7k stars
- optimum huggingface, 3.5k stars
Tool data from the GitHub API, fetched 19 Nov 2026, 15:43 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.