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

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run Gemma 4 12B?

Gemma · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Gemma 4 12B at FP16 · 23.8 GB weights · 80–120 tok/s on a NVIDIA H100 SXM (80GB).

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
25.0 GB
Weights + KV cache + runtime overhead
Estimated generation
80–120 tok/s
Estimated first token
~0.5s

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 NVIDIA H100 SXM (80GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K4.7 GB5.9 GB210–314 tok/sRuns great
Q3_K_M5.7 GB6.9 GB193–289 tok/sRuns great
Q4_K_M7.1 GB8.3 GB173–260 tok/sRuns great
Q5_K_M8.4 GB9.6 GB159–239 tok/sRuns great
Q6_K9.8 GB11.0 GB146–219 tok/sRuns great
Q8_012.7 GB13.9 GB125–187 tok/sRuns great
FP1623.8 GB25.0 GB80–120 tok/sRuns great
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsGemma 4 12B on other machinesWhat to buy to run it →

Ran Gemma 4 12B on a NVIDIA H100 SXM (80GB)? Add your real numbers →