Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
51.4 tok/s
TTFT
3767 ms
Safe context
22K
Memory
14.5 GB / 20.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Tight fit | 55.7 tok/s | 5058 ms | 33K |
| Chat | C | Runs well | 55.7 tok/s | 1897 ms | 12K |
| Coding | B | Runs well | 51.4 tok/s | 3767 ms | 22K |
| RAG | C | Tight fit | 55.7 tok/s | 6323 ms | 33K |
| Reasoning | B | Runs well | 55.7 tok/s | 4110 ms | 22K |
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on RTX A4500 20GB (20.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | D35 |
Q3_K_S | 3 | 7.2 GB | Low | D37 |
NVFP4 | 4 |
ollama run phi-4-reasoning-plus-14bhuggingface-cli download phi-4-reasoning-plus-14b8.2 GB |
| Medium |
| D38 |
Q4_K_M | 4 | 9.0 GB | Medium | D39 |
Q5_K_M | 5 | 10.6 GB | High | C41 |
Q6_K | 6 | 12.1 GB | High | C42 |
Q8_0Best for your GPU | 8 | 15.7 GB | Very High | C44 |
F16 | 16 | 30.1 GB | Maximum | F0 |