GLM-4.6V-Flash 9B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The 9B vision-language model in the GLM-4.6V family, built for low-latency multimodal work. The real small GLM: GLM-4.7 is a ~400B MoE and has no 9B checkpoint.
GLM-4.6V-Flash 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.
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 Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 3.8 GB | ~144 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 4.6 GB | ~123 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 6.2 GB | ~98 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 7.2 GB | ~87 tok/s | Fits | |
| Q6_K 6.56 bpw | 8.2 GB | ~78 tok/s | Fits | |
| Q8_0 8.50 bpw | 10.4 GB | ~64 tok/s | Fits | |
| F16 16.00 bpw | 18.8 GB | ~37 tok/s | Fits |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GLM-4.6V-Flash 9B VRAM calculator →
Get GLM-4.6V-Flash 9B running
The cheapest catalogued GPU that runs GLM-4.6V-Flash 9B is the Intel Arc B570 (10 GB).
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.
How to run GLM-4.6V-Flash 9B
Install Ollama, then run:
ollama run glm-4-6vSpecifications
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. Still unconfirmed: context.
- Parameters
- 9 Billion
- Context window
- 65,536
- Architecture
- Dense vision-language
- Provider
- Zhipu AI (Z.ai)
- Licence
- MIT
- Practical deployment
- Laptop
- Specified at
- Q4_K_M
- System RAM
- 16 GB
- Record updated
- 2026-09-19
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.
GLM-4.6V-Flash 9B — frequently asked questions
How much VRAM does GLM-4.6V-Flash 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-4.6V-Flash 9B run on an RTX 4090 (24 GB)?
Yes. GLM-4.6V-Flash 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-4.6V-Flash 9B locally?
Install Ollama and run `ollama run glm-4-6v`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.