Can a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) run Granite 4.2 30B?

Yes — Granite 4.2 30B runs at Q2_K (10.9 GB) at about 13–20 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

How much memory does Granite 4.2 30B need?

Granite 4.2 30B needs about 12.7 GB at 4K context at its smallest quantization. A AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) has 64.0 GB.

Yes — Granite 4.2 30B runs on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) at Q2_K

Yes — it runs great.

Runs great

Best fit: Granite 4.2 30B at Q2_K · 10.9 GB weights · 13–20 tok/s on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB).

Arena Text Overall · style-controlled

1,340Q2_K untested

granite-4.2-30b · published configuration reference · Q2_K not tested

Arena Text Overall (style-controlled), exact published entry granite-4.2-30b, 2026-10-08: reference rating 1,339.7. Published confidence bounds 1,329.2–1,350.1. 3,410 votes. Published granite-4.2-30b 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: 12.7 GB; Weights + KV cache + runtime overhead
Estimated generation: 13–20 tok/s
Estimated first token: ~16s

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.

Granite 4.2 30B 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	10.9 GB	12.7 GB	13–20 tok/s	Runs great
Q3_K_M	14.1 GB	16.0 GB	11–16 tok/s	Tight / slow
Q4_K_M	17.7 GB	19.6 GB	9–13 tok/s	Tight / slow
Q5_K_M	20.8 GB	22.7 GB	8–11 tok/s	Tight / slow
Q6_K	24.0 GB	25.9 GB	7–10 tok/s	Tight / slow
Q8_0	31.1 GB	33.0 GB	5–8 tok/s	Tight / slow
FP16	58.6 GB	60.4 GB	— not resident	Won't fit

Open the full calculator →Everything a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB) runs Granite 4.2 30B on other machines What to buy to run it →

Ran Granite 4.2 30B on a AMD Ryzen AI Max+ 395 “Strix Halo” (64GB)? Add your real numbers →