Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
107.6 tok/s
TTFT
1798 ms
Safe context
31K
Memory
6.3 GB / 12.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 71.8 tok/s | 3924 ms | 55K |
| Chat | C | Runs well | 71.8 tok/s | 1471 ms | 15K |
| Coding | C | Runs well | 107.6 tok/s | 1798 ms | 31K |
| RAG | C | Runs well | 71.8 tok/s | 4905 ms | 55K |
| Reasoning | C | Runs well | 71.8 tok/s | 3188 ms | 31K |
How HelpingAI2.5 5B i1 (5B params) fits at each quantization level on Intel Arc B580 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.0 GB | Low | D32 |
Q3_K_S | 3 | 2.5 GB | Low | D33 |
NVFP4 | 4 |
2.8 GB |
| Medium |
| D34 |
Q4_K_M | 4 | 3.1 GB | Medium | D34 |
Q5_K_M | 5 | 3.6 GB | High | D35 |
Q6_K | 6 | 4.1 GB | High | D36 |
Q8_0Best for your GPU | 8 | 5.4 GB | Very High | D38 |
F16 | 16 | 10.3 GB | Maximum | C44 |