Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
181.8 tok/s
TTFT
1065 ms
Safe context
32K
Memory
5.5 GB / 11.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 164.1 tok/s | 1716 ms | 59K |
| Chat | C | Runs well | 164.1 tok/s | 644 ms | 16K |
| Coding | C | Runs well | 181.8 tok/s | 1065 ms | 32K |
| RAG | C | Runs well | 164.1 tok/s | 2145 ms | 59K |
| Reasoning | C | Runs well | 164.1 tok/s | 1394 ms | 32K |
How Qwen3.5 4B (4B params) fits at each quantization level on RTX 2080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.6 GB | Low | D33 |
Q3_K_S | 3 | 2.0 GB | Low | D33 |
NVFP4 | 4 |
2.2 GB |
| Medium |
| D34 |
Q4_K_M | 4 | 2.4 GB | Medium | D34 |
Q5_K_M | 5 | 2.9 GB | High | D35 |
Q6_K | 6 | 3.3 GB | High | D36 |
Q8_0Best for your GPU | 8 | 4.3 GB | Very High | D38 |
F16 | 16 | 8.2 GB | Maximum | C44 |