Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
105.9 tok/s
TTFT
1828 ms
Safe context
23K
Memory
11.0 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 95.6 tok/s | 2946 ms | 40K |
| Chat | B | Runs well | 95.6 tok/s | 1105 ms | 13K |
| Coding | B | Runs well | 105.9 tok/s | 1828 ms | 23K |
| RAG | B | Runs well | 95.6 tok/s | 3682 ms | 40K |
| Reasoning | B | Runs well | 95.6 tok/s | 2393 ms | 23K |
How Nous Hermes 2 SOLAR 10.7B (10.699999809265137B params) fits at each quantization level on RTX 5080 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.2 GB | Low | D35 |
Q3_K_S | 3 | 5.2 GB | Low | D36 |
NVFP4 | 4 |
| Medium |
| D37 |
Q4_K_M | 4 | 6.5 GB | Medium | D38 |
Q5_K_M | 5 | 7.7 GB | High | D39 |
Q6_K | 6 | 8.8 GB | High | C41 |
Q8_0Best for your GPU | 8 | 11.4 GB | Very High | C44 |
F16 | 16 | 21.9 GB | Maximum | F0 |