Can it run?
Runs well
Using Q4_K_M in vLLM
Fit status
Runs well
Decode
230.9 tok/s
TTFT
839 ms
Safe context
31K
Memory
94.0 GB / 180.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 269.3 tok/s | 1045 ms | 61K |
| Chat | C | Runs well | 269.3 tok/s | 392 ms | 15K |
| Coding | C | Runs well | 230.9 tok/s | 839 ms | 31K |
| RAG | C | Runs well | 269.3 tok/s | 1307 ms | 61K |
| Reasoning | C | Runs well | 269.3 tok/s | 849 ms | 31K |
How Mistral Small 4 119B (119B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | D35 |
Q3_K_S | 3 | 58.3 GB | Low | D36 |
NVFP4 | 4 |
huggingface-cli download mistral-small-4-119b66.6 GB |
| Medium |
| D37 |
Q4_K_M | 4 | 72.6 GB | Medium | D38 |
Q5_K_M | 5 | 85.7 GB | High | D40 |
Q6_K | 6 | 97.6 GB | High | C41 |
Q8_0Best for your GPU | 8 | 127.3 GB | Very High | C45 |
F16 | 16 | 244.0 GB | Maximum | F0 |