What GPU do you need to run GLM 5.1?
754B params 198K max context Tool use
The smallest GPU memory that runs GLM 5.1 well is 512 GB (Q4_K_M, e.g. M3 Ultra). 2 of 132 GPUs run it well.
MMLU 86.9
VRAM needed per quantization
| Quantization | Weights | 16K context | 32K context | Full 198K |
|---|---|---|---|---|
| Q4_K_M | 459.7 GB | 461.0 GB | 462.4 GB | 476.3 GB |
| Q8_0 | 801.3 GB | 802.7 GB | 804.0 GB | 818.0 GB |
Weights plus fp16 KV cache. Leave ~1 GB headroom for the inference engine.
GPUs that can run GLM 5.1
Best quantization that fits on each GPU, with the context and speed it gets. For chips with several memory sizes, the smallest that works is shown.