LocalClaw/LLM/Xing4.0-29B-A4B
Open-weight MoE

Xing4.0-29B-A4B

Catalogue summary: Official China Telecom XingChen-AGI Apache 2.0 MoE release with 29B total parameters, 4B active parameters, 256K native context and an official IQ4_NL GGUF path for llama.cpp-class local inference on 24GB GPU workstations.

Repository editorial metadata; verify comparative claims in the linked upstream material.

32 GB catalogue minimum32 GB RAMIQ4_NL GGUFCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
29B (4B active, MoE)
Minimum RAM
32 GB
Model size
20.1 GB
Quantization
IQ4_NL GGUF

Can Xing4.0-29B-A4B run locally?

Xing4.0-29B-A4B has a catalogue minimum of 32 GB RAM with IQ4_NL GGUF. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use xing4.0-29b-a4b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-23): XingChen-AGI/Xing4.0-29B-A4B-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningagenticpowerlong-contexttool-callingmoe

Install path

01
Check RAM fitMinimum 32 GB RAM. Start with the IQ4_NL GGUF quant.
02
Load the modelSearch xing4.0-29b-a4b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: xing
  • Parameters: 29B (4B active, MoE)
  • Recommended quantization: IQ4_NL GGUF
  • Catalogue minimum RAM: 32 GB
  • Catalogue model size: 20.1 GB
  • Tags: chat, code, reasoning, agentic, power, long-context, tool-calling, moe

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • agentic
  • power
  • long-context

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
7
quality
9
coding
10
reasoning
9

Technical notes

Developer
China Telecom Artificial Intelligence Technology / XingChen-AGI
License
Apache 2.0
Context window
262,144 tokens
Architecture
29B-parameter Mixture-of-Experts causal language model with about 4B active parameters per token, MLA attention, 64 routed experts, 4 active experts, one shared expert and Xing4.0 custom model code.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Comfortable headroomMac mini M4 Pro 48GBMobile workstationMacBook Pro M4 Max 36GBPower-user picks32GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Nex-N2.5-mini 35B MoEOccamy-1.0 35B (3B active, MoE)Nemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Qwen3-Coder-Next 80B (3B active, MoE)K2-Horizon-32B 32B denseQwen 3.6 35B-A3B 35B (3B active, MoE)Qwen3.8-27B 27BMuse Glimmer 30B 29.8B multimodal

Where to go next