AMD Radeon RX 7900 XTX × Phi-4 14B
Can the RX 7900 XTX run Phi-4 14B?
Yes
Yes. The RX 7900 XTX can run Phi-4 14B at up to Q8_0 (needs ~18.6 GB of 22.8 GB usable), at an estimated ~79.1 tokens/sec at Q4_K_M.
Speed is estimated from memory bandwidth (no measured benchmark for this device). No direct public benchmark of this exact pair is recorded yet.
By quantization (8K context)
| Quant | Memory needed | Fits? | Est. tok/s |
|---|---|---|---|
| Q3_K_M | 9.9 GB | ✅ | ~98.3 |
| Q4_K_M | 11.7 GB | ✅ | ~79.1 |
| Q5_K_M | 13.3 GB | ✅ | ~67.3 |
| Q6_K | 15.0 GB | ✅ | ~58.1 |
| Q8_0 | 18.6 GB | ✅ | ~45.1 |
| F16 | 32.8 GB | ❌ | — |
Fastest hardware for Phi-4 14B
- NVIDIA GeForce RTX 5090 — ~124 tok/s at Q4_K_M
- NVIDIA GeForce RTX 4090 — ~79.9 tok/s at Q4_K_M
- NVIDIA GeForce RTX 5080 — ~78.1 tok/s at Q4_K_M
- NVIDIA GeForce RTX 5070 Ti — ~75.9 tok/s at Q4_K_M
- NVIDIA GeForce RTX 3080 10GB — ~74.5 tok/s at Q3_K_M
No suitable GPU? Rent one by the hour on Vast.ai or RunPod (affiliate links).
Get new models & benchmarks in your inbox
No spam. Unsubscribe anytime by replying to any email.