Can the Radeon RX 7900 XTX run Phi-4 (14B)?
Fits comfortably at Q4_K_M.
Phi-4 (14B) is 14.7B parameters. At Q4_K_M the weights are about 8.2 GiB; with the 1.5 GiB runtime reserve that is 9.7 GiB against the card's 24GB, leaving about 14.3 GiB for context.
All three quants
24GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 8.2 GiB | 9.7 GiB | Fits comfortably | 14.3 GiB |
| Q8_0near-lossless | 14.5 GiB | 16.0 GiB | Fits comfortably | 8.0 GiB |
| FP16full weights | 27.4 GiB | 28.9 GiB | Only with CPU offload | short 4.9 GiB |
Verdict rules: fits comfortably when weights plus reserve sit within 85% of VRAM; tight when they fit with little left for context; CPU offload when they exceed VRAM by up to 2x (runs, slowly, with layers in system RAM); no beyond that. The KV cache per token depends on the model's architecture and is not modelled here.
Good match. Get the card.
The Radeon RX 7900 XTX clears Phi-4 (14B) at Q4_K_M and at Q8_0. Live listings below; this page was rebuilt 2026-08-23.
Amazon links may earn us a commission. Prices move daily; the links open live listings.
About the model
Phi-4 (14B) by Microsoft: 16,384-token native context, text, released 2024 under the MIT. Model card → · Hosted pricing on PicksByModel →