Can a AMD Instinct MI355X (288GB) run Granite 4.2 8B?

Yes — Granite 4.2 8B runs at FP16 (17.6 GB) at about 172–258 tok/s on a AMD Instinct MI355X (288GB).

How much memory does Granite 4.2 8B need?

Granite 4.2 8B needs about 4.9 GB at 4K context at its smallest quantization. A AMD Instinct MI355X (288GB) has 288.0 GB.

Yes — Granite 4.2 8B runs on a AMD Instinct MI355X (288GB) at FP16

Yes — it runs great.

Runs great

Best fit: Granite 4.2 8B at FP16 · 17.6 GB weights · 172–258 tok/s on a AMD Instinct MI355X (288GB).

Arena Text Overall · style-controlled

1,290FP16 untested

granite-4.2-8b · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry granite-4.2-8b, 2026-10-08: reference rating 1,290.2. Published confidence bounds 1,279.1–1,301.4. 3,253 votes. Published granite-4.2-8b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected FP16 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: 19.1 GB; Weights + KV cache + runtime overhead
Estimated generation: 172–258 tok/s
Estimated first token: ~0.2s

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 8B quantizations on AMD Instinct MI355X (288GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	3.4 GB	4.9 GB	293–439 tok/s	Runs great
Q3_K_M	4.4 GB	5.8 GB	280–420 tok/s	Runs great
Q4_K_M	5.4 GB	6.8 GB	267–401 tok/s	Runs great
Q5_K_M	6.3 GB	7.7 GB	257–385 tok/s	Runs great
Q6_K	7.2 GB	8.7 GB	246–369 tok/s	Runs great
Q8_0	9.4 GB	10.8 GB	226–339 tok/s	Runs great
FP16	17.6 GB	19.1 GB	172–258 tok/s	Runs great

Open the full calculator →Everything a AMD Instinct MI355X (288GB) runs Granite 4.2 8B on other machines What to buy to run it →

Ran Granite 4.2 8B on a AMD Instinct MI355X (288GB)? Add your real numbers →