Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
191.5 tok/s
TTFT
1011 ms
Safe context
32K
Memory
3.0 GB / 6.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 191.5 tok/s | 1470 ms | 33K |
| Chat | C | Runs well | 191.5 tok/s | 551 ms | 16K |
| Coding | C | Runs well | 191.5 tok/s | 1011 ms | 32K |
| RAG | C | Runs well | 191.5 tok/s | 1838 ms | 33K |
| Reasoning | C | Runs well | 191.5 tok/s | 1195 ms | 32K |
How Qwen 3 0.6B (0.6000000238418579B params) fits at each quantization level on RTX 2060 6GB (6.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.2 GB | Low | D28 |
Q3_K_S | 3 | 0.3 GB | Low | D29 |
NVFP4 | 4 | 0.3 GB | Medium | D29 |
Q4_K_M | 4 | 0.4 GB | Medium | D29 |
Q5_K_M | 5 | 0.4 GB | High | D29 |
Q6_K | 6 | 0.5 GB | High | D29 |
Q8_0 | 8 | 0.6 GB | Very High | D30 |
F16Best for your GPU | 16 | 1.2 GB | Maximum | D32 |
ollama run qwen-3-0.6bhuggingface-cli download qwen-3-0.6b