Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a AMD Instinct MI355X (288GB) run Gemma 3 27B?

Gemma · Gemma · estimated for a 288.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Gemma 3 27B at FP16 · 54.0 GB weights · 83–125 tok/s on a AMD Instinct MI355X (288GB).

Arena Text Overall · style-controlled

1,365FP16 untested

gemma-3-27b-it · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry gemma-3-27b-it, 2026-10-08: reference rating 1,365.4. Published confidence bounds 1,361.7–1,369.1. 46,672 votes. Published gemma-3-27b-it 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
55.6 GB
Weights + KV cache + runtime overhead
Estimated generation
83–125 tok/s
Estimated first token
~0.7s

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.

Gemma 3 27B quantizations on AMD Instinct MI355X (288GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K10.5 GB12.1 GB216–324 tok/sRuns great
Q3_K_M13.4 GB15.0 GB195–292 tok/sRuns great
Q4_K_M16.6 GB18.1 GB177–265 tok/sRuns great
Q5_K_M19.3 GB20.8 GB163–245 tok/sRuns great
Q6_K22.2 GB23.7 GB151–227 tok/sRuns great
Q8_028.7 GB30.3 GB130–194 tok/sRuns great
FP1654.0 GB55.6 GB83–125 tok/sRuns great

Ran Gemma 3 27B on a AMD Instinct MI355X (288GB)? Add your real numbers →