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

Can I run this LLM?

Can a NVIDIA H100 SXM (80GB) run GLM-4 9B?

GLM · MIT · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: GLM-4 9B at FP16 · 18.8 GB weights · 96–144 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
19.8 GB
Weights + KV cache + runtime overhead
Estimated generation
96–144 tok/s
Estimated first token
~0.4s

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.

GLM-4 9B quantizations on NVIDIA H100 SXM (80GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K4.0 GB5.0 GB227–340 tok/sRuns great
Q3_K_M5.0 GB5.9 GB208–312 tok/sRuns great
Q4_K_M6.2 GB7.1 GB189–284 tok/sRuns great
Q5_K_M7.1 GB8.0 GB177–266 tok/sRuns great
Q6_K8.3 GB9.2 GB163–245 tok/sRuns great
Q8_010.0 GB11.0 GB146–220 tok/sRuns great
FP1618.8 GB19.8 GB96–144 tok/sRuns great
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runsGLM-4 9B on other machinesWhat to buy to run it →

Ran GLM-4 9B on a NVIDIA H100 SXM (80GB)? Add your real numbers →