Zhipu AI (Z.ai)9B~6 GB VRAM at Q4_K_M

GLM-4 9B — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

GLM-4-9B, Z.ai's compact bilingual model. Strong Chinese-English performance and general reasoning; runs comfortably on 8 GB VRAM. Previously listed as 'GLM-4.7 9B', which does not exist - GLM-4.7 is a ~400B MoE whose small sibling is GLM-4.7-Flash at 30B-A3B. The Ollama tag recorded here, glm4:9b, pulls GLM-4-9B, so the record was correct apart from its name.

GLM-4 9B needs about 6 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.

Logic87
Creative84
Coding82

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
3.8 GB~144 tok/sFits
Q3_K_M
3.41 bpw
4.6 GB~123 tok/sFits
Q4_K_M
4.83 bpw
6.2 GB~98 tok/sFits
Q5_K_M
5.67 bpw
7.2 GB~87 tok/sFits
Q6_K
6.56 bpw
8.2 GB~78 tok/sFits
Q8_0
8.50 bpw
10.4 GB~64 tok/sFits
F16
16.00 bpw
18.8 GB~37 tok/sFits

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GLM-4 9B VRAM calculator →

Get GLM-4 9B running

The cheapest catalogued GPU that runs GLM-4 9B is the Intel Arc B570 (10 GB).

Buy this hardware Intel Arc B570 10GB — 10 GB VRAM · 150 W board powerDeploy in the cloud now RTX 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.

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.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

How to run GLM-4 9B

Install Ollama, then run:

ollama run glm4:9b
Weights on Hugging Face: THUDM/glm-4-9b-chat ↗

Specifications

Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed.

Parameters
9 Billion
Context window
128,000
Architecture
Dense
Provider
Zhipu AI (Z.ai)
Licence
Apache 2.0
Practical deployment
Laptop
Specified at
Q4_K_M
System RAM
16 GB
Record updated
2026-02-14
LicenceApache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forchatmultilingualreasoningchinese

Can I run GLM-4 9B on my GPU?

Other GLM-4.7 / GLM-Z1 sizes

GLM-4 9B — frequently asked questions

How much VRAM does GLM-4 9B need?

About 6 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-4 9B run on an RTX 4090 (24 GB)?

Yes. GLM-4 9B needs about 6 GB at Q4_K_M, inside a 24 GB card, at an estimated 98 tokens/sec.

How do I run GLM-4 9B locally?

Install Ollama and run `ollama run glm4:9b`. 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 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.