GLM-4.7-Flash 30B-A3B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
Z.ai's local-first coder: a 30B-total / 3B-active MoE that delivers 30B-class output quality at roughly 3B-class speed, which is what makes it practical on a single consumer card. Q4_K_M is ~19 GB, so it fits a 24GB GPU with room for a long context; q8_0 (~32 GB) and bf16 (~60 GB) tags exist for workstation setups. 198K context and an MIT license make it one of the least restrictive local coding models available.
GLM-4.7-Flash 30B-A3B needs about 19 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 Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.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 | 10.7 GB | ~212 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 13.6 GB | ~196 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 18.9 GB | ~172 tok/s | Fits | |
| Q5_K_M 5.67 bpw | 22.1 GB | ~160 tok/s | Tight | |
| Q6_K 6.56 bpw | 25.4 GB | ~22 tok/s | Offload | |
| Q8_0 8.50 bpw | 32.7 GB | ~20 tok/s | Offload | |
| F16 16.00 bpw | 60.8 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GLM-4.7-Flash 30B-A3B VRAM calculator →
Get GLM-4.7-Flash 30B-A3B running
The cheapest catalogued GPU that runs GLM-4.7-Flash 30B-A3B is the AMD Radeon RX 7900 XTX (24 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-4.7-Flash 30B-A3B
Install Ollama, then run:
ollama run glm-4.7-flashSpecifications
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- Parameters
- 30 Billion (3B active)
- Context window
- 198,000
- Architecture
- Mixture-of-Experts
- Provider
- Zhipu AI (Z.ai)
- Licence
- MIT
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 32 GB
- Record updated
- 2026-08-15
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.
Can I run GLM-4.7-Flash 30B-A3B on my GPU?
- GLM-4.7-Flash 30B-A3B on AMD Radeon RX 7900 XT
- GLM-4.7-Flash 30B-A3B on AMD Radeon RX 7900 XTX
- GLM-4.7-Flash 30B-A3B on AMD Radeon RX 9060 XT 8GB
- GLM-4.7-Flash 30B-A3B on Apple M1 Pro
- GLM-4.7-Flash 30B-A3B on Apple M2 Pro
- GLM-4.7-Flash 30B-A3B on Apple M3 Pro
- GLM-4.7-Flash 30B-A3B on Apple M4
- GLM-4.7-Flash 30B-A3B on Apple M5
- GLM-4.7-Flash 30B-A3B on Intel Arc B570
- GLM-4.7-Flash 30B-A3B on Intel Arc B580
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 3060 (12GB)
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 3070
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 3070 Ti
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 3080 (10GB)
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 3090
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 4060
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 4070
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 4070 Super
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 4070 Ti
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 4090
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 5060
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 5060 Ti 8GB
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 5070
- GLM-4.7-Flash 30B-A3B on NVIDIA GeForce RTX 5090
- GLM-4.7-Flash 30B-A3B on NVIDIA L40S
- GLM-4.7-Flash 30B-A3B on NVIDIA RTX 6000 Ada Generation
Other GLM-4.7 / GLM-Z1 sizes
GLM-4.7-Flash 30B-A3B — frequently asked questions
How much VRAM does GLM-4.7-Flash 30B-A3B need?
About 19 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-4.7-Flash 30B-A3B run on an RTX 4090 (24 GB)?
Yes. GLM-4.7-Flash 30B-A3B needs about 19 GB at Q4_K_M, inside a 24 GB card, at an estimated 172 tokens/sec.
How do I run GLM-4.7-Flash 30B-A3B locally?
Install Ollama and run `ollama run glm-4.7-flash`. 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.