Can a AMD Instinct MI300X (192GB) run Granite 4.2 8B?

Yes — Granite 4.2 8B runs at FP16 (17.6 GB) at about 135–203 tok/s on a AMD Instinct MI300X (192GB).

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 MI300X (192GB) has 192.0 GB.

Yes — Granite 4.2 8B runs on a AMD Instinct MI300X (192GB) at FP16

Yes — it runs great.

Runs great

Best fit: Granite 4.2 8B at FP16 · 17.6 GB weights · 135–203 tok/s on a AMD Instinct MI300X (192GB).

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: 135–203 tok/s
Estimated first token: ~0.4s

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 MI300X (192GB), 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	265–398 tok/s	Runs great
Q3_K_M	4.4 GB	5.8 GB	250–374 tok/s	Runs great
Q4_K_M	5.4 GB	6.8 GB	235–352 tok/s	Runs great
Q5_K_M	6.3 GB	7.7 GB	223–334 tok/s	Runs great
Q6_K	7.2 GB	8.7 GB	211–316 tok/s	Runs great
Q8_0	9.4 GB	10.8 GB	189–284 tok/s	Runs great
FP16	17.6 GB	19.1 GB	135–203 tok/s	Runs great

Open the full calculator →Everything a AMD Instinct MI300X (192GB) runs Granite 4.2 8B on other machines What to buy to run it →

Ran Granite 4.2 8B on a AMD Instinct MI300X (192GB)? Add your real numbers →