---
title: XingChen-AGI/Xing4.0-29B-A4B-w8a8
url: https://recentmodel.com/models/XingChen-AGI/Xing4.0-29B-A4B-w8a8/
status: archived · low-signal
published: 2026-10-16T06:52:19Z
updated: 2026-10-18T11:22:04Z
source: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-w8a8
---

# XingChen-AGI/Xing4.0-29B-A4B-w8a8

Xing4.0-29B-A4B is a large language model in the Xing series (formerly TeleChat), developed by China Telecom Artificial Intelligence Technology Co., Ltd. Mixture-of-experts, 29B total, 4B active (64 experts, 4 per token). Context: 256K tokens (config). License: apache-2.0.


- **Org:** XingChen-AGI
- **Released:** 2026-10-16
- **Status:** archived · low-signal
- **License:** apache-2.0 (permissive)
- **Parameters:** 29.0B total, 4.0B active
- **Architecture:** MoE · 64 experts, 4/token · Xing4_0ForCausalLM
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 2 HF likes · 136 downloads
- **Archived:** 2026-10-18 (no longer listed by the collector; stats as last seen)

## Runs on

estimate from params; sizing calculation, not tested.

- Q4 ~18.8 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.2 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~59.4 GB (estimated): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-w8a8)