With 16 GB of VRAM, the RTX 4080 SUPER runs Phi-4 14B at Q4_K_M entirely on the GPU with an 8K context (about 11.2 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 11.2 GB and fits in the 15.5 GB available, with 4.3 GB to spare.
~11.2 GB (10.8 GB–11.8 GB) needed · estimate
Fits entirely in VRAM · 4.3 GB left
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Phi-4 14B Q8_08K~17.6 GB · 7.5–14 tok/s estimate | CPU/GPU offload |
|---|---|
| Phi-4 14B Q6_K8K~14.2 GB · 40–54 tok/s estimate | Compatible |
| Phi-4 14B Q5_K_M8K~12.8 GB · 44–60 tok/s estimate | Excellent |
| Phi-4 14B Q4_K_M8K~11.2 GB · 51–69 tok/s estimate | Excellent |
| Phi-4 14B IQ4_XS8K~10.2 GB · 56–78 tok/s estimate | Excellent |
| Phi-4 14B Q3_K_M8K~9.6 GB · 59–83 tok/s estimate | Excellent |
Prices and links follow the market you choose.
16 GB GDDR6X · 736 GB/s · 320 W
ExcellentRuns Phi-4 14B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
