Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
94.4 tok/s
TTFT
2420 ms
Safe context
43K
Memory
106.6 GB / 288.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 95.7 tok/s | 2941 ms | 75K |
| Chat | C | Runs well | 95.7 tok/s | 1103 ms | 23K |
| Coding | C | Runs well | 94.4 tok/s | 2420 ms | 43K |
| RAG | C | Runs well | 95.7 tok/s | 3677 ms | 75K |
| Reasoning | C | Runs well | 95.7 tok/s | 2390 ms | 43K |
How Solar Open 100B i1 (100B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | D32 |
Q3_K_S | 3 | 49.0 GB | Low | D33 |
NVFP4 | 4 |
56.0 GB |
| Medium |
| D33 |
Q4_K_M | 4 | 61.0 GB | Medium | D33 |
Q5_K_M | 5 | 72.0 GB | High | D34 |
Q6_K | 6 | 82.0 GB | High | D35 |
Q8_0 | 8 | 107.0 GB | Very High | D37 |
F16Best for your GPU | 16 | 205.0 GB | Maximum | C44 |