Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
129.8 tok/s
TTFT
1491 ms
Safe context
38K
Memory
5.0 GB / 12.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 129.8 tok/s | 2169 ms | 74K |
| Chat | C | Runs well | 129.8 tok/s | 813 ms | 19K |
| Coding | C | Runs well | 129.8 tok/s | 1491 ms | 38K |
| RAG | C | Runs well | 129.8 tok/s | 2711 ms | 74K |
| Reasoning | C | Runs well | 129.8 tok/s | 1762 ms | 38K |
How Qwen2.5 3B Instruct (3B params) fits at each quantization level on RTX 3060 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | D32 |
Q3_K_S | 3 | 1.5 GB | Low | D32 |
NVFP4 | 4 | 1.7 GB | Medium | D32 |
Q4_K_M | 4 | 1.8 GB | Medium | D33 |
Q5_K_M | 5 | 2.2 GB | High | D33 |
Q6_K | 6 | 2.5 GB | High | D34 |
Q8_0 | 8 | 3.2 GB | Very High | D35 |
F16Best for your GPU | 16 | 6.1 GB | Maximum | C40 |
