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

Can I run this LLM?

Can a AMD RX 9070 XT (16GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Gemma 4 12B at Q6_K · 9.8 GB weights · 41–62 tok/s on a AMD RX 9070 XT (16GB).

Arena Text Overall · style-controlled

UnratedNo exact match

No reviewed exact Arena match

No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.

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
11.0 GB
Weights + KV cache + runtime overhead
Estimated generation
41–62 tok/s
Estimated first token
~2.9s

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 4 12B quantizations on AMD RX 9070 XT (16GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K4.7 GB5.9 GB75–112 tok/sRuns great
Q3_K_M5.7 GB6.9 GB64–97 tok/sRuns great
Q4_K_M7.1 GB8.3 GB54–81 tok/sRuns great
Q5_K_M8.4 GB9.6 GB47–71 tok/sRuns great
Q6_K9.8 GB11.0 GB41–62 tok/sRuns great
Q8_012.7 GB13.9 GB33–50 tok/sTight / slow
FP1623.8 GB25.0 GB— not residentWon't fit

Ran Gemma 4 12B on a AMD RX 9070 XT (16GB)? Add your real numbers →