NVIDIA · 80 GB HBM2e · 2039 GB/s bandwidth ·
Z.ai · 110.5B (active 12B) · MoE · model ctx up to 128K
Yes — the A100 80GB SXM4 (80 GB HBM2e) can run GLM-4.5-Air. At Q4 with the default 8K context it needs ≈ 64.18 GB VRAM (weights 60.78 GB + KV cache 2.4 GB + 1 GB runtime overhead), which fits within 80 GB. Decode at Q4/8K: ≈ 108.1 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
Yes
108.1est.
Q4
8K default
64.18 GB
Yes
108.1est.
Q4
32K
71.38 GB
Yes
108.1est.
FP16
4K
223.2 GB
No
10.9est.
FP16
8K default
224.4 GB
No
10.8est.
FP16
32K
231.6 GB
No
10.1est.
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).