Can a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) run Phi-4 14B?

Yes — Phi-4 14B runs at Q6_K (12.0 GB) at about 12–19 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

How much memory does Phi-4 14B need?

Phi-4 14B needs about 7.2 GB at 4K context at its smallest quantization. A AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) has 128.0 GB.

Yes — Phi-4 14B runs on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) at Q6_K

Yes — it runs great.

Runs great

Best fit: Phi-4 14B at Q6_K · 12.0 GB weights · 12–19 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB).

Arena Text Overall · style-controlled

1,256Q6_K untested

phi-4 · published configuration reference · Q6_K not tested

Arena Text Overall (style-controlled), exact published entry phi-4, 2026-10-08: reference rating 1,256.3. Published confidence bounds 1,251.7–1,260.9. 24,126 votes. Published phi-4 configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q6_K has not been measured by this Arena entry. No quantization quality adjustment is applied.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context: 13.7 GB; Weights + KV cache + runtime overhead
Estimated generation: 12–19 tok/s
Estimated first token: ~8.0s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

Phi-4 14B quantizations on AMD Ryzen AI Max+ 395 “Strix Halo” (128GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	5.6 GB	7.2 GB	23–35 tok/s	Runs great
Q3_K_M	7.2 GB	8.8 GB	19–29 tok/s	Runs great
Q4_K_M	8.9 GB	10.5 GB	16–24 tok/s	Runs great
Q5_K_M	10.4 GB	12.0 GB	14–21 tok/s	Runs great
Q6_K	12.0 GB	13.7 GB	12–19 tok/s	Runs great
Q8_0	15.6 GB	17.2 GB	10–15 tok/s	Tight / slow
FP16	29.3 GB	31.0 GB	6–8 tok/s	Tight / slow

Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runs Phi-4 14B on other machines What to buy to run it →

Ran Phi-4 14B on a AMD Ryzen AI Max+ 395 “Strix Halo” (128GB)? Add your real numbers →