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

Can I run this LLM?

Can a NVIDIA L40S (48GB) run MiniCPM5 2B?

MiniCPM · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: MiniCPM5 2B at FP16 · 5.0 GB weights · 92–138 tok/s on a NVIDIA L40S (48GB).

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
6.0 GB
Weights + KV cache + runtime overhead
Estimated generation
92–138 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.

MiniCPM5 2B quantizations on NVIDIA L40S (48GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K1.0 GB2.0 GB218–327 tok/sRuns great
Q3_K_M1.2 GB2.2 GB202–303 tok/sRuns great
Q4_K_M1.6 GB2.6 GB180–271 tok/sRuns great
Q5_K_M1.9 GB2.9 GB166–250 tok/sRuns great
Q6_K2.1 GB3.1 GB159–238 tok/sRuns great
Q8_02.7 GB3.7 GB139–208 tok/sRuns great
FP165.0 GB6.0 GB92–138 tok/sRuns great
Open the full calculator →Everything a NVIDIA L40S (48GB) runsMiniCPM5 2B on other machinesWhat to buy to run it →

Ran MiniCPM5 2B on a NVIDIA L40S (48GB)? Add your real numbers →