Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Qwen3.8 27B?

Yes — Qwen3.8 27B runs at Q2_K (10.8 GB) at about 14–21 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

How much memory does Qwen3.8 27B need?

Qwen3.8 27B needs about 11.9 GB at 4K context at its smallest quantization. A AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) has 64.0 GB.

Yes — Qwen3.8 27B runs on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) at Q2_K

Yes — it runs great.

Runs great

Best fit: Qwen3.8 27B at Q2_K · 10.8 GB weights · 14–21 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Arena Text Overall · style-controlled

1,438Q2_K untested

qwen3.8-27b · published configuration reference · Q2_K not tested

Arena Text Overall (style-controlled), exact published entry qwen3.8-27b, 2026-10-08: reference rating 1,438.1. Published confidence bounds 1,432.8–1,443.4. 20,711 votes. Published qwen3.8-27b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q2_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: 11.9 GB; Weights + KV cache + runtime overhead
Estimated generation: 14–21 tok/s
Estimated first token: ~14s

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.

Qwen3.8 27B quantizations on AMD Ryzen AI Max+ 395 “Strix Halo” (64GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	10.8 GB	11.9 GB	14–21 tok/s	Runs great
Q3_K_M	13.4 GB	14.5 GB	12–18 tok/s	Tight / slow
Q4_K_M	17.4 GB	18.5 GB	9–14 tok/s	Tight / slow
Q5_K_M	20.9 GB	22.0 GB	8–12 tok/s	Tight / slow
Q6_K	23.9 GB	24.9 GB	7–10 tok/s	Tight / slow
Q8_0	29.1 GB	30.2 GB	6–9 tok/s	Tight / slow
FP16	54.7 GB	55.7 GB	— not resident	Won't fit

Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runs Qwen3.8 27B on other machines What to buy to run it →

Ran Qwen3.8 27B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →