Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
56.7 tok/s
TTFT
3417 ms
Safe context
25K
Memory
91.9 GB / 141.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 66.1 tok/s | 4260 ms | 42K |
| Chat | C | Runs well | 66.1 tok/s | 1598 ms | 13K |
| Coding | C | Runs well | 56.7 tok/s | 3417 ms | 25K |
| RAG | B | Runs well | 66.1 tok/s | 5325 ms | 42K |
| Reasoning | C | Runs well | 66.1 tok/s | 3462 ms | 25K |
How Solar Open 100B i1 (100B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | D35 |
Q3_K_S | 3 | 49.0 GB | Low | D36 |
NVFP4 | 4 |
56.0 GB |
| Medium |
| D37 |
Q4_K_M | 4 | 61.0 GB | Medium | D38 |
Q5_K_M | 5 | 72.0 GB | High | D40 |
Q6_K | 6 | 82.0 GB | High | C41 |
Q8_0Best for your GPU | 8 | 107.0 GB | Very High | C44 |
F16 | 16 | 205.0 GB | Maximum | F0 |
