Text model · GLM
GLGLM-4 9B requirements
GLM family · 9B params · released Jun 2024. Minimum to run at Q4_K_M: Nvidia GeForce RTX 3060 (12GB).
LicenseGLM-4 License· Conditional↓ 56.8K/mo♥ 707on HuggingFace
Q4_K_M
5.82 GB
Q8_0
9.31 GB
Total @ Q4 (4k)
~7.3 GB
Context
128 k
Quantization sizes
GGUF quantson disk
| Quantization | Size on disk |
|---|---|
| Q2_K | 3.8 GB est |
| Q3_K_M | 4.4 GB est |
| Q4_K_M (default) | 5.82 GB |
| Q5_K_M | 6.4 GB est |
| Q6_K | 7.4 GB est |
| Q8_0 | 9.31 GB |
| FP16 | 18 GB est |
Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.
Run it
Ollama
$
ollama run glm4:9b llama.cpp
$
llama-cli -hf bartowski/glm-4-9b-chat-GGUF:Q4_K_M LM Studio
$
lms get bartowski/glm-4-9b-chat-GGUF Which devices can run GLM-4 9B?
Apple Silicon Macs
RAM-only laptops
iPhone & iPad
Android
NVIDIA GPUs
AMD GPUs
FAQ
How much VRAM or RAM does GLM-4 9B need?
At Q4_K_M, GLM-4 9B needs about 7.3 GB (weights ~5.82 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~10.8 GB.
Can GLM-4 9B run on a laptop?
GLM-4 9B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.
Can I use GLM-4 9B commercially?
Conditionally. GLM-4 Model License: review terms for commercial use.
Zhipu GLM-4 9B, multilingual, 128K context. Q4_K_M and Q8_0 sizes from the bartowski GGUF repo.
Sources
Memory figures are estimates. See methodology.