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

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run Muse Glimmer 30B?

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

Yes — it runs great.

Runs great

Best fit: Muse Glimmer 30B at FP16 · 55.7 GB weights · 40–59 tok/s on a NVIDIA H100 SXM (80GB).

Arena Text Overall · style-controlled

UnratedAmbiguous match

Ambiguous Arena identity; unrated

Arena identity is ambiguous. The Arena identifier omits the 30B size. An independent Arena alias-to-release binding is not yet verified. No rating is assigned or used for ranking. 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
56.7 GB
Weights + KV cache + runtime overhead
Estimated generation
40–59 tok/s
Estimated first token
~1.3s

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.

Muse Glimmer 30B quantizations on NVIDIA H100 SXM (80GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K11.0 GB12.0 GB138–207 tok/sRuns great
Q3_K_M14.0 GB14.9 GB119–178 tok/sRuns great
Q4_K_M17.3 GB18.2 GB102–153 tok/sRuns great
Q5_K_M20.1 GB21.0 GB92–138 tok/sRuns great
Q6_K23.4 GB24.3 GB82–123 tok/sRuns great
Q8_029.6 GB30.5 GB68–102 tok/sRuns great
FP1655.7 GB56.7 GB40–59 tok/sRuns great
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsMuse Glimmer 30B on other machinesWhat to buy to run it →

Ran Muse Glimmer 30B on a NVIDIA H100 SXM (80GB)? Add your real numbers →