Z.ai
GLM-4.5 Air 106B-A12B
MoE
110,5B
Parameters · 12B active
68,5 Go
Q4_K_M file
≥ 70,0 Go
Recommended VRAM
131 072
Max context
Not measured yet
No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.
Measure my card →Which cards should it fit on?
Cards on the site whose video memory covers the recommended 70,0 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.
Technical sheet
- Published
- 2025-07-20
- Architecture
- 46 layers · 8 KV heads · dimension 128
- Attention
- Standard: every layer keeps the whole context in memory.
- Context cache (f16)
- ≈ 180 MB per 1,000 tokens · 5,8 Go for 32,768 tokens
- GGUF file
- bartowski/zai-org_GLM-4.5-Air-GGUF · 2 files Download (68,5 Go)
- Official repo
- zai-org/GLM-4.5-Air
Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.