Can it run?
Too heavy
Using Q4_K_M in vLLM
Fit status
Too heavy
Decode
40.6 tok/s
TTFT
4770 ms
Safe context
6K
Memory
481.3 GB / 188.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 40.6 tok/s | 6938 ms | 12K |
| Chat | F | Too heavy | 40.6 tok/s | 2602 ms | 4K |
| Coding | F | Too heavy | 40.6 tok/s | 4770 ms | 6K |
| RAG | F | Too heavy | 40.6 tok/s | 8673 ms | 12K |
| Reasoning | F | Too heavy | 40.6 tok/s | 5638 ms | 6K |
How GLM-5 (744B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 290.2 GB | Low | F0 |
Q3_K_S | 3 | 364.6 GB | Low | F0 |
NVFP4 | 4 | 416.6 GB | Medium | F0 |
Q4_K_M | 4 | 453.8 GB | Medium | F0 |
Q5_K_M | 5 | 535.7 GB | High | F0 |
Q6_K | 6 | 610.1 GB | High | F0 |
Q8_0 | 8 | 796.1 GB | Very High | F0 |
F16 | 16 | 1525.2 GB | Maximum | F0 |
