GLM-5 32B — VRAM, Speed & Local Setup

作者： Jakub Rusinowski · 最后更新： 2026年4月10日

Model library → GLM-5 / GLM-5.1 → GLM-5 32B

Mid-range GLM-5 with excellent balance of capability and resource requirements. Strong at agentic reasoning chains and long-context document processing. MIT license allows unrestricted commercial deployment.

GLM-5 32B needs about 20 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters32 Billion
Context window128,000
ArchitectureGLM (General Language Model)
ProviderZhipu AI (Z.ai)
LicenceMIT
Specified atQ4_K_M
System RAM32 GB
Record updated2026-04-10

Licence

MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K10.5 GB11.3 GB~58 tok/s (est.)Fits comfortably
Q3_K_M13.6 GB14.4 GB~46 tok/s (est.)Fits comfortably
Q4_K_M19.3 GB20.1 GB~34 tok/s (est.)Fits comfortably
Q5_K_M22.7 GB23.5 GB~30 tok/s (est.)Tight fit
Q6_K26.2 GB27.0 GB~4 tok/s (est.)Offloads to system RAM (slow)
Q8_034.0 GB34.8 GB~3 tok/s (est.)Offloads to system RAM (slow)
F1664.0 GB64.8 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the GLM-5 32B VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board powerDeploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs GLM-5 32B is the AMD Radeon RX 7900 XT (20 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026年价格波动较大——请以当前商品页价格为准。
在亚马逊查看价格

How to Run GLM-5 32B

Install Ollama, then run:

ollama run hf.co/THUDM/GLM-5-32B-Chat-Q4_K_M

Weights on Hugging Face: THUDM/GLM-5-32B-Chat.

Published Benchmark Scores

Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.

BenchmarkScoreProvenance
MMLU86.4 / 100 %reported
HumanEval88.7 / 100 %reported

Best for: agentic, reasoning, document processing, coding, enterprise.

Can I Run GLM-5 32B on My GPU?

Other GLM-5 / GLM-5.1 Sizes

GLM-5 32B — Frequently Asked Questions

How much VRAM does GLM-5 32B need?
About 20 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does GLM-5 32B run on an RTX 4090 (24 GB)?
Yes. GLM-5 32B needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 34 tokens/sec.
How do I run GLM-5 32B locally?
Install Ollama and run `ollama run hf.co/THUDM/GLM-5-32B-Chat-Q4_K_M`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does GLM-5 / GLM-5.1 come in?
GLM-5 9B (6 GB), GLM-5 32B (20 GB), GLM-5.1 72B (44 GB), GLM-5 744B (450 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All GLM-5 / GLM-5.1 models | VRAM calculator | Build a PC for this model | Check your own hardware