Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
111.1 tok/s
TTFT
1743 ms
Safe context
24K
Memory
10.6 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 100.3 tok/s | 2808 ms | 42K |
| Chat | C | Runs well | 100.3 tok/s | 1053 ms | 13K |
| Coding | B | Runs well | 111.1 tok/s | 1743 ms | 24K |
| RAG | B | Runs well | 100.3 tok/s | 3510 ms | 42K |
| Reasoning | B | Runs well | 100.3 tok/s | 2281 ms | 24K |
How Helply 10.2b chat i1 (10.199999809265137B params) fits at each quantization level on RTX 5080 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.0 GB | Low | D34 |
Q3_K_S | 3 | 5.0 GB | Low | D35 |
NVFP4 | 4 |
| Medium |
| D36 |
Q4_K_M | 4 | 6.2 GB | Medium | D37 |
Q5_K_M | 5 | 7.3 GB | High | D38 |
Q6_K | 6 | 8.4 GB | High | D40 |
Q8_0Best for your GPU | 8 | 10.9 GB | Very High | C43 |
F16 | 16 | 20.9 GB | Maximum | F0 |
