Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
166.0 tok/s
TTFT
1166 ms
Safe context
43K
Memory
35.3 GB / 96.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 166.0 tok/s | 1697 ms | 76K |
| Chat | C | Runs well | 166.0 tok/s | 636 ms | 23K |
| Coding | C | Runs well | 166.0 tok/s | 1166 ms | 43K |
| RAG | C | Runs well | 166.0 tok/s | 2121 ms | 76K |
| Reasoning | C | Runs well | 166.0 tok/s | 1378 ms | 43K |
How Qwen 2.5 Coder 32B (32B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.5 GB | Low | D32 |
Q3_K_S | 3 | 15.7 GB | Low | D33 |
NVFP4 | 4 | 17.9 GB | Medium | D33 |
Q4_K_M | 4 | 19.5 GB | Medium | D34 |
Q5_K_M | 5 | 23.0 GB | High | D35 |
Q6_K | 6 | 26.2 GB | High | D35 |
Q8_0 | 8 | 34.2 GB | Very High | D37 |
F16Best for your GPU | 16 | 65.6 GB | Maximum | C44 |
ollama run qwen-2.5-coder-32bhuggingface-cli download qwen-2.5-coder-32b