Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
60.8 tok/s
TTFT
3183 ms
Safe context
23K
Memory
90.6 GB / 128.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 60.8 tok/s | 4630 ms | 39K |
| Chat | C | Runs well | 60.8 tok/s | 1736 ms | 12K |
| Coding | B | Runs well | 60.8 tok/s | 3183 ms | 23K |
| RAG | C | Tight fit | 60.8 tok/s | 5788 ms | 39K |
| Reasoning | B | Runs well | 60.8 tok/s | 3762 ms | 23K |
How Solar Open 100B i1 (100B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 39.0 GB | Low | D35 |
Q3_K_S | 3 | 49.0 GB | Low | D37 |
NVFP4 | 4 |
56.0 GB |
| Medium |
| D38 |
Q4_K_M | 4 | 61.0 GB | Medium | D39 |
Q5_K_M | 5 | 72.0 GB | High | C41 |
Q6_KBest for your GPU | 6 | 82.0 GB | High | C43 |
Q8_0 | 8 | 107.0 GB | Very High | C44 |
F16 | 16 | 205.0 GB | Maximum | F0 |