LocalClaw/LLM/GLM-5.2 (744B MoE)
Open-weight local LLM

GLM-5.2 (744B MoE)

Catalogue summary: Z.ai flagship open model for long-horizon coding, reasoning and agentic work. 744B total, 40B active, 1M-token context, MIT license. Unsloth Dynamic GGUF makes it technically local, but it needs workstation/server-class memory: ~245GB total memory for 2-bit and 372GB+ for 4-bit.

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

256 GB catalogue minimum256 GB RAMUD-IQ2_MCoding assistant
Choose an app

Only verified options can be opened. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
Open in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use 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
744B (40B active)
Minimum RAM
256 GB
Model size
239 GB
Quantization
UD-IQ2_M

Can GLM-5.2 (744B MoE) run locally?

GLM-5.2 (744B MoE) has a catalogue minimum of 256 GB RAM with UD-IQ2_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat glm-5.2 as a server-grade catalogue target. Use the verified artefact with a compatible multi-GPU or distributed runtime and follow its upstream instructions; this is not a one-click desktop LM Studio recommendation.

Public GGUF repository (verified 2026-09-07): unsloth/GLM-5.2-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningqualityagenticlong-contextgeneral

Deployment path

01
Check RAM fitServer-grade target. Plan for 256 GB class multi-GPU memory.
02
Load the modelUse glm-5.2 only with a compatible server-grade or distributed runtime; confirm the exact artefact and upstream instructions first.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: glm
  • Parameters: 744B (40B active)
  • Recommended quantization: UD-IQ2_M
  • Catalogue minimum RAM: 256 GB
  • Catalogue model size: 239 GB
  • Tags: chat, code, reasoning, quality, agentic, long-context, general

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
  • quality
  • agentic
  • long-context

Capability profile

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

speed
2
quality
10
coding
10
reasoning
10

Technical notes

Developer
Z.ai
License
MIT
Context window
1,048,576 tokens
Architecture
GLM MoE DSA with 744B total parameters, about 40B active parameters, 8 experts per token, IndexShare sparse attention and a 1M-token context window. The practical local path is the Unsloth Dynamic GGUF release.

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.

Very large memoryMac Studio Ultra classCheck model size firstNVIDIA GB10 / server optionsMore practical alternativesCompare smaller models

Related catalogue entries

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

GLM 4.7 355B (32B active, MoE)GLM 4.6 (355B MoE) 355B (32B active)GLM-5.3-Flash 320B (18B active, MoE)GLM 4.5 Air (MoE) 106B (12B active, MoE)GLM-4 (32B) 32BGLM-4 (9B) 9BGLM-5.1 754B MoEGLM 4.7 Flash 14B

Where to go next