Written by Jakub Rusinowski · Last updated August 15, 2026
Model library → GLM-4.7 / GLM-Z1 → GLM-4.7-Flash 30B-A3B
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.
| Parameters | 30 Billion (3B active) |
| Context window | 198,000 |
| Architecture | Mixture-of-Experts |
| Provider | Zhipu AI (Z.ai) |
| Licence | MIT |
| Specified at | Q4_K_M |
| System RAM | 32 GB |
| Record updated | 2026-08-15 |
MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
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.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 9.9 GB | 10.7 GB | ~212 tok/s (est.) | Fits comfortably |
| Q3_K_M | 12.8 GB | 13.6 GB | ~196 tok/s (est.) | Fits comfortably |
| Q4_K_M | 18.1 GB | 18.9 GB | ~172 tok/s (est.) | Fits comfortably |
| Q5_K_M | 21.3 GB | 22.1 GB | ~160 tok/s (est.) | Tight fit |
| Q6_K | 24.6 GB | 25.4 GB | ~22 tok/s (est.) | Offloads to system RAM (slow) |
| Q8_0 | 31.9 GB | 32.7 GB | ~20 tok/s (est.) | Offloads to system RAM (slow) |
| F16 | 60.0 GB | 60.8 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the GLM-4.7-Flash 30B-A3B VRAM calculator.
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.
The cheapest catalogued GPU that runs GLM-4.7-Flash 30B-A3B is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama, then run:
ollama run glm-4.7-flashWeights on Hugging Face: zai-org/GLM-4.7-Flash.
Best for: coding, agentic tasks, local first, long documents.
← All GLM-4.7 / GLM-Z1 models | VRAM calculator | Build a PC for this model | Check your own hardware