GLM-Z1 32B (Reasoning) — VRAM, Speed & Local Setup

Written by Jakub Rusinowski · Last updated February 14, 2026

Model library → GLM-4.7 / GLM-Z1 → GLM-Z1 32B (Reasoning)

Reasoning-specialized GLM variant. Near-GPT-5.2 on the AI Index. Best for math, logic, and scientific reasoning tasks.

GLM-Z1 32B (Reasoning) 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
ArchitectureDense
ProviderZhipu AI (Z.ai)
LicenceApache 2.0
Specified atQ4_K_M
System RAM48 GB
Record updated2026-02-14

Licence

Apache-2.0 — 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-Z1 32B (Reasoning) 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-Z1 32B (Reasoning) is the AMD Radeon RX 7900 XT (20 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

How to Run GLM-Z1 32B (Reasoning)

Install Ollama, then run:

ollama run glm-z1:32b

Weights on Hugging Face: THUDM/GLM-Z1-32B.

Best for: reasoning, math, science, logic.

Can I Run GLM-Z1 32B (Reasoning) on My GPU?

Other GLM-4.7 / GLM-Z1 Sizes

GLM-Z1 32B (Reasoning) — Frequently Asked Questions

How much VRAM does GLM-Z1 32B (Reasoning) 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-Z1 32B (Reasoning) run on an RTX 4090 (24 GB)?
Yes. GLM-Z1 32B (Reasoning) needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 34 tokens/sec.
How do I run GLM-Z1 32B (Reasoning) locally?
Install Ollama and run `ollama run glm-z1:32b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does GLM-4.7 / GLM-Z1 come in?
GLM-4.7 9B (6 GB), GLM-Z1 32B (Reasoning) (20 GB), GLM-4.7-Flash 30B-A3B (19 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All GLM-4.7 / GLM-Z1 models | VRAM calculator | Build a PC for this model | Check your own hardware