Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
133.9 tok/s
TTFT
1446 ms
Safe context
27K
Memory
3.5 GB / 6.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 133.9 tok/s | 2103 ms | 55K |
| Chat | C | Runs well | 133.9 tok/s | 789 ms | 14K |
| Coding | C | Runs well | 133.9 tok/s | 1446 ms | 27K |
| RAG | C | Runs well | 133.9 tok/s | 2628 ms | 55K |
| Reasoning | C | Runs well | 133.9 tok/s | 1708 ms | 27K |
How Falcon H1 1.5B Instruct (1.5B params) fits at each quantization level on Intel Arc A380 6GB (6.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.6 GB | Low | D31 |
Q3_K_S | 3 | 0.7 GB | Low | D31 |
NVFP4 | 4 |
0.8 GB |
| Medium |
| D32 |
Q4_K_M | 4 | 0.9 GB | Medium | D32 |
Q5_K_M | 5 | 1.1 GB | High | D33 |
Q6_K | 6 | 1.2 GB | High | D33 |
Q8_0 | 8 | 1.6 GB | Very High | D34 |
F16Best for your GPU | 16 | 3.1 GB | Maximum | D40 |