Can it run?
Runs well
Using Q3_K_M in Ollama
Fit status
Runs well
Decode
53.8 tok/s
TTFT
3601 ms
Safe context
24K
Memory
94.1 GB / 141.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 62.7 tok/s | 4489 ms | 40K |
| Chat | C | Runs well | 62.7 tok/s | 1684 ms | 13K |
| Coding | C | Runs well | 53.8 tok/s | 3601 ms | 24K |
| RAG | B | Runs well | 62.7 tok/s | 5612 ms | 40K |
| Reasoning | B | Runs well | 62.7 tok/s | 3648 ms | 24K |
How Qwen3.5 122B A10B (122B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 47.6 GB | Low | D37 |
Q3_K_S | 3 | 59.8 GB | Low | D39 |
NVFP4 | 4 |
huggingface-cli download hf-unsloth--qwen3-5-122b-a10b-gguf68.3 GB |
| Medium |
| D40 |
Q4_K_M | 4 | 74.4 GB | Medium | C41 |
Q5_K_M | 5 | 87.8 GB | High | C43 |
Q6_KBest for your GPU | 6 | 100.0 GB | High | C45 |
Q8_0 | 8 | 130.5 GB | Very High | C45 |
F16 | 16 | 250.1 GB | Maximum | F0 |