Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
80.6 tok/s
TTFT
2401 ms
Safe context
4K
Memory
3.1 GB / 4.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 54.9 tok/s | 5131 ms | 4K |
| Chat | C | Runs well | 54.9 tok/s | 1924 ms | 4K |
| Coding | B | Runs well | 80.6 tok/s | 2401 ms | 4K |
| RAG | C | Runs well | 54.9 tok/s | 6414 ms | 4K |
| Reasoning | C | Runs well | 54.9 tok/s | 4169 ms | 4K |
How TinyLlama 1.1B (1.100000023841858B params) fits at each quantization level on Intel Arc A370M 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.4 GB | Low | D30 |
Q3_K_S | 3 | 0.5 GB | Low | D31 |
NVFP4 | 4 |
ollama run tinyllama-1.1bhuggingface-cli download tinyllama-1.1b| Medium |
| D31 |
Q4_K_M | 4 | 0.7 GB | Medium | D32 |
Q5_K_M | 5 | 0.8 GB | High | D32 |
Q6_K | 6 | 0.9 GB | High | D33 |
Q8_0Best for your GPU | 8 | 1.2 GB | Very High | D35 |
F16 | 16 | 2.3 GB | Maximum | C40 |