RTX 2060 6GBBudget pickC184.7 tok/s decode
~$349 MSRP
Can it run?
Tight fit
Using Q4_K_M in Ollama
Fit status
Tight fit
Decode
52.9 tok/s
TTFT
3658 ms
Safe context
19K
Memory
3.4 GB / 4.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 52.9 tok/s | 5321 ms | 33K |
| Chat | C | Tight fit | 52.9 tok/s | 1995 ms | 9K |
| Coding | C | Tight fit | 52.9 tok/s | 3658 ms | 19K |
| RAG | C | Tight fit | 52.9 tok/s | 6651 ms | 33K |
| Reasoning | C | Tight fit | 52.9 tok/s | 4323 ms | 19K |
How Qwen 3 1.7B (1.7000000476837158B params) fits at each quantization level on Intel Arc A370M 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 0.7 GB | Low | D32 |
Q3_K_S | 3 | 0.8 GB | Low | D32 |
NVFP4 | 4 | 1.0 GB | Medium | D33 |
Q4_K_M | 4 | 1.0 GB | Medium | D33 |
Q5_K_M | 5 | 1.2 GB | High | D34 |
Q6_K | 6 | 1.4 GB | High | D35 |
Q8_0Best for your GPU | 8 | 1.8 GB | Very High | D38 |
F16 | 16 | 3.5 GB | Maximum | C43 |
ollama run qwen-3-1.7bhuggingface-cli download qwen-3-1.7bUpgrade options
RTX 2060 6GBBudget pick~$349 MSRP
GTX 1060 6GBBiggest leap
Intel Arc Pro A40 6GBIntel upgrade