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

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Kimi K2.7 (MoE)?

Kimi · See model card · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Kimi K2.7 (MoE) at Q3_K_M · 463.6 GB weights · 25–37 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

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
464.7 GB
Weights + KV cache + runtime overhead
Estimated generation
25–37 tok/s
Estimated first token
~1.5s

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.

Kimi K2.7 (MoE) quantizations on NVIDIA GH200 Grace Hopper (144GB HBM + 480GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K339.5 GB340.5 GB37–55 tok/sRuns great
Q3_K_M463.6 GB464.7 GB25–37 tok/sRuns great
Q4_K_M583.7 GB584.8 GB— not residentWon't fit

Ran Kimi K2.7 (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →