Can a NVIDIA L40S (48GB) run GLM-4.7 Flash (MoE)?

Yes — GLM-4.7 Flash (MoE) runs at Q8_0 (31.8 GB) at about 124–186 tok/s on a NVIDIA L40S (48GB).

How much memory does GLM-4.7 Flash (MoE) need?

GLM-4.7 Flash (MoE) needs about 12.4 GB at 4K context at its smallest quantization. A NVIDIA L40S (48GB) has 48.0 GB.

Yes — GLM-4.7 Flash (MoE) runs on a NVIDIA L40S (48GB) at Q8_0

Yes — it runs great.

Runs great

Best fit: GLM-4.7 Flash (MoE) at Q8_0 · 31.8 GB weights · 124–186 tok/s on a NVIDIA L40S (48GB).

Arena Text Overall · style-controlled

1,365Q8_0 untested

glm-4.7-flash · published configuration reference · Q8_0 not tested

Arena Text Overall (style-controlled), exact published entry glm-4.7-flash, 2026-10-08: reference rating 1,364.7. Published confidence bounds 1,359–1,370.4. 12,020 votes. Published glm-4.7-flash configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q8_0 has not been measured by this Arena entry. No quantization quality adjustment is applied.

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: 32.9 GB; Weights + KV cache + runtime overhead
Estimated generation: 124–186 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-4.7 Flash (MoE) quantizations on NVIDIA L40S (48GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	11.3 GB	12.4 GB	206–309 tok/s	Runs great
Q3_K_M	14.6 GB	15.6 GB	186–280 tok/s	Runs great
Q4_K_M	18.3 GB	19.3 GB	168–252 tok/s	Runs great
Q5_K_M	21.4 GB	22.4 GB	155–233 tok/s	Runs great
Q6_K	24.7 GB	25.7 GB	144–216 tok/s	Runs great
Q8_0	31.8 GB	32.9 GB	124–186 tok/s	Runs great
FP16	59.9 GB	60.9 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA L40S (48GB) runs GLM-4.7 Flash (MoE) on other machines What to buy to run it →

Ran GLM-4.7 Flash (MoE) on a NVIDIA L40S (48GB)? Add your real numbers →