Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
93.0 tok/s
TTFT
2082 ms
Safe context
16K
Memory
11.2 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 93.0 tok/s | 3028 ms | 16K |
| Chat | B | Runs well | 93.0 tok/s | 1136 ms | 12K |
| Coding | B | Runs well | 93.0 tok/s | 2082 ms | 16K |
| RAG | B | Runs well | 93.0 tok/s | 3785 ms | 16K |
| Reasoning | B | Runs well | 93.0 tok/s | 2460 ms | 16K |
How Llama 3.2 11B Vision (11B params) fits at each quantization level on RTX 5080 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 4.3 GB | Low | D35 |
Q3_K_S | 3 | 5.4 GB | Low | D36 |
NVFP4 | 4 | 6.2 GB | Medium | D38 |
Q4_K_M | 4 | 6.7 GB | Medium | D38 |
Q5_K_M | 5 | 7.9 GB | High | D40 |
Q6_K | 6 | 9.0 GB | High | C41 |
Q8_0Best for your GPU | 8 | 11.8 GB | Very High | C44 |
F16 | 16 | 22.5 GB | Maximum | F0 |
ollama run llama-3.2-11b-visionhuggingface-cli download llama-3.2-11b-vision