Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
77.0 tok/s
TTFT
2513 ms
Safe context
4K
Memory
12.8 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 77.0 tok/s | 3656 ms | 4K |
| Chat | B | Runs well | 77.0 tok/s | 1371 ms | 4K |
| Coding | B | Runs well | 77.0 tok/s | 2513 ms | 4K |
| RAG | C | Tight fit | 77.0 tok/s | 4569 ms | 4K |
| Reasoning | B | Runs well | 77.0 tok/s | 2970 ms | 4K |
How LLaVA 1.6 13B (13B params) fits at each quantization level on RTX 4080 Super 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | D36 |
Q3_K_S | 3 | 6.4 GB | Low | D37 |
NVFP4 | 4 | 7.3 GB | Medium | D39 |
Q4_K_M | 4 | 7.9 GB | Medium | D39 |
Q5_K_M | 5 | 9.4 GB | High | C41 |
Q6_KBest for your GPU | 6 | 10.7 GB | High | C43 |
Q8_0 | 8 | 13.9 GB | Very High | C44 |
F16 | 16 | 26.7 GB | Maximum | F0 |
ollama run llava-1.6-13bhuggingface-cli download llava-1.6-13b