Tencent/AngelSlim
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #21 among LLM repositories tracked this week, and #21 over the last 30 days; #478 of 2,794 repositories GStars tracks this week (top 17%).
No releases in the last 90 days; the most recent was 118 days ago, with 37 contributors on GitHub.
Gained 68% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides a comprehensive Python toolkit for compressing large AI models using quantization and speculative decoding techniques.
- Enables efficient, one-click model compression with continuous innovation and support for state-of-the-art algorithms like FP8 and ternary quantization.
- Use for compressing large language models (LLMs) such as Qwen3 and Hunyuan to reduce memory footprint and accelerate inference on single GPUs.
- Use for quantizing vision-language models (VLMs) and diffusion models to optimize multimodal AI workloads with advanced caching and quantization strategies.
- Use for deploying compressed speech models (TTS/ASR) with hardware-efficient quantization and speculative decoding to improve real-time audio processing performance.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
A more accessible, comprehensive, and efficient toolkit for large model compression.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
193+26
Open issues
68+3
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 18, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| DietrichGebert/ponytail | 173.5K | +9.2K | 75 | 6 days ago |
| xerj-org/xerj | 13.1K | +8.1K | 75 | today |
| tashfeenahmed/freellmapi | 39.6K | +3.9K | 75 | 1 day ago |
| JuliusBrussee/caveman | 114.4K | +2.2K | 75 | 9 days ago |
| thesysdev/openui | 13.1K | +2.1K | 75 | 7 days ago |
| Tencent/AngelSlim | 1.8K | +0 | 75 | 118 days ago |
| Category median | 39.6K | +3.9K | 75 | — |
Also by Tencent
Other repositories from this maintainer that GStars tracks
- Go35.1K stars
WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
- TypeScript9.1K stars
BrowserSkill
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
- Python6.9K stars
AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
- TypeScript5.4K stars
teamai-cli
Make Every Team AI Native
- TypeScript4.9K stars
cherry-markdown
✨ A Markdown Editor
Discover Repositories
Search across tracked repositories by name or description