Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
66.9 tok/s
TTFT
2895 ms
Safe context
23K
Memory
7.7 GB / 11.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 66.9 tok/s | 4211 ms | 40K |
| Chat | C | Runs well | 66.9 tok/s | 1579 ms | 12K |
| Coding | B | Runs well | 66.9 tok/s | 2895 ms | 23K |
| RAG | B | Runs well | 66.9 tok/s | 5263 ms | 40K |
| Reasoning | B | Runs well | 66.9 tok/s | 3421 ms | 23K |
How Qwen 2.5 Coder 7B (7B params) fits at each quantization level on GTX 1080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | D34 |
Q3_K_S | 3 | 3.4 GB | Low | D35 |
NVFP4 | 4 | 3.9 GB | Medium | D36 |
Q4_K_M | 4 | 4.3 GB | Medium | D37 |
Q5_K_M | 5 | 5.0 GB | High | D38 |
Q6_K | 6 | 5.7 GB | High | D40 |
Q8_0Best for your GPU | 8 | 7.5 GB | Very High | C43 |
F16 | 16 | 14.3 GB | Maximum | F0 |
ollama run qwen-2.5-coder-7bhuggingface-cli download qwen-2.5-coder-7b