Can L40S 48GB run GLM-4.5-Air?

NVIDIA · 48 GB GDDR6 · 864 GB/s bandwidth · Z.ai · 110.5B (active 12B) · MoE · model ctx up to 128K

No — GLM-4.5-Air at Q4 needs ≈ 62.98 GB even at 4K context, beyond the L40S 48GB's 48 GB GDDR6. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 73.2 tok/s (estimated, batch 1). FP16 needs ≈ 224.4 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	62.98 GB	No	76.0 est.
Q4	8K default	64.18 GB	No	73.2 est.
Q4	32K	71.38 GB	No	59.2 est.
FP16	4K	223.2 GB	No	—
FP16	8K default	224.4 GB	No	—
FP16	32K	231.6 GB	No	—

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	L40S 48GB VRAM
Q4	60.78 GB	2.4 GB	1 GB	64.18 GB	48 GB
FP16	221.0 GB	2.4 GB	1 GB	224.4 GB	48 GB

Other GPUs that run GLM-4.5-Air

• B200 192GB SXM — ≈424.2 tok/s Q4 est.
• MI300X 192GB — ≈281.1 tok/s Q4 est.
• H200 141GB SXM5 — ≈254.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈177.7 tok/s Q4 est.
• Gaudi 3 128GB — ≈173.7 tok/s Q4 est.
• A100 80GB SXM4 — ≈108.1 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — ≈43.4 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈42.4 tok/s Q4 est.

All GPUs for GLM-4.5-Air →

Other models for the L40S 48GB

• Qwen3-0.6B — ≈687.3 tok/s Q4 est.
• gemma-3-1b-it — ≈549.8 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈458.2 tok/s Q4 est.
• Qwen3-1.7B — ≈274.9 tok/s Q4 est.
• Qwen3-30B-A3B — ≈183.3 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈183.3 tok/s Q4 est.
• GLM-4.7-Flash — ≈183.3 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈183.3 tok/s Q4 est.

All models on the L40S 48GB →