---
title: "Tencent's AngelSlim Squeezes 235B Models onto a Single GPU"
subtitle: "Tencent's AngelSlim open-sources a full LLM compression stack covering quantization down to 1.25-bit, Eagle3 speculative decoding, and sparse attention — all in one pip install."
url: "https://alphasignal.ai/news/tencent-s-angelslim-squeezes-235b-models-onto-a-single-gpu"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-20T02:36:22.000Z"
updated: "2026-06-20T07:56:52.868Z"
type: "Repo"
topics:
  - "Gpus"
  - "Open Source"
subtopics:
  - "Quantization"
  - "Kernels"
  - "Edge Deployment"
upvotes: 2846
source_url: "https://github.com/Tencent/AngelSlim"
comments: 0
truncated: true
---

# Tencent's AngelSlim Squeezes 235B Models onto a Single GPU

> Tencent's AngelSlim open-sources a full LLM compression stack covering quantization down to 1.25-bit, Eagle3 speculative decoding, and sparse attention — all in one pip install.

Squeezing a 235-billion-parameter model onto a single GPU used to require a team of engineers and months of custom work. [AngelSlim](https://github.com/Tencent/AngelSlim), the compression toolkit from Tencent's Hunyuan AI Infra team, is trying to make that a one-liner. The project has been iterating rapidly since its initial release, and it now covers the full compression pipeline , quantization, speculative decoding, sparse attention, token pruning, and diffusion model optimization , across LLMs, vision-language models, and audio models.

## One toolkit, every compression knob

AngelSlim is a comprehensive toolkit for large model compression developed by the Tencent Hunyuan team, consolidating cutting-edge algorithms including quantization, speculative decoding, token pruning, and distillation into a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. The scope is unusually broad: it supports LLMs, VLMs, diffusion models (image, video, 3D), and speech models (TTS/ASR) under a single API.

The model coverage is similarly wide. Out of the box, AngelSlim supports:

* **LLMs:** Hunyuan Dense/MoE, Qwen3, DeepSeek-R1/V3, GLM-4.6, Qwen2.5, Kimi-K2
* **VLMs:** Hunyuan-VL, HunyuanOCR, Qwen3-VL, Qwen2.5-VL
* **Diffusion:** Hunyuan-Image/Video/3D, FLUX, Wan, SDXL
* **Audio:** Qwen3-Omni, Qwen2-Audio, Fun-CosyVoice3

## Quantization from FP8 down to 1.25-bit

AngelSlim integrates state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. The quantization menu spans a wide range of formats:

* **FP8-Static / FP8-Dynamic** , the workhorse for production deployments
* **INT8-Dynamic, INT4-GPTQ, INT4-AWQ, NVFP4** , for aggressive size reduction
* **LeptoQuant** , a custom FP8 algorithm. LeptoQuant introduces Dynamic Outlier Isolation Scale, observing that weight distributions often follow a Laplacian-like peak with significant outliers, and searches for optimal scaling values to isolate those outliers and preserve the representational fidelity of the original distribution.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [GitHub - Tencent/AngelSlim](https://github.com/Tencent/AngelSlim)
- [AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression (arXiv:2602.21233)](https://arxiv.org/abs/2602.21233)
- [AngelSlim Documentation](https://angelslim.readthedocs.io)
- [AngelSlim Hugging Face Organization](https://huggingface.co/AngelSlim)
- [Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs](https://huggingface.co/blog/lujangusface/tw-eagle3-gpu)