GLM-4.5-Air: VRAM requirements & speed
GLM-4.5-Air (110.47B MoE, 12B active, mit). Native context 128k. Smallest GGUF: 72.98 GB.
Memory needed by quantization and context
GGUF file size plus f16 KV cache (and fixed overhead of ~1 GB per GPU not shown). Source: unsloth/GLM-4.5-Air-GGUF.
| Quant | File | +8k ctx | +32k ctx | +128k ctx |
|---|---|---|---|---|
| Q4_K_M | 72.98 GB | 74.5 GB | 79.2 GB | 97.7 GB |
| Q5_K_M | 83.52 GB | 85.1 GB | 89.7 GB | 108.2 GB |
| Q6_K | 99.01 GB | 100.6 GB | 105.2 GB | 123.7 GB |
| Q8_0 | 117.46 GB | 119.0 GB | 123.6 GB | 142.2 GB |
KV cache size by context length
Computed from the model's attention layout.
| Context | f16 | q8_0 | q4_0 |
|---|---|---|---|
| 8k | 1.54 GB | 0.82 GB | 0.43 GB |
| 32k | 6.17 GB | 3.28 GB | 1.74 GB |
| 128k | 24.70 GB | 13.12 GB | 6.95 GB |
Which hardware runs GLM-4.5-Air? · 16k context
Discrete GPUs are modelled with 32 GB of system RAM available for offload. Does not fit even with offload: RTX 3090 24GB, RTX 4090 24GB, RTX 5090 32GB, RTX 3060 12GB (32GB RAM), 8GB VRAM class (RTX 4060 8GB, 32GB RAM), 16GB VRAM class (RTX 4060 Ti 16GB, 32GB RAM), RTX 5070 12GB, RTX 4070 12GB, RTX 5070 Ti 16GB, RTX 5080 16GB, AMD RX 7900 XTX 24GB, Mac Studio (2025) M3 Ultra 96GB, Mac mini / iMac M4 16GB, Mac mini (2024) M4 Pro 64GB, MacBook Pro 14/16 M5 Pro 48GB, Mac mini M6 32GB, MacBook Air M5 32GB.
Links
Model card · GGUF files · Open in the advisor · last verified 2026-10-14
FAQ
How much VRAM does GLM-4.5-Air need?
The smallest quant (Q4_K_M) is 72.98 GB, so you need roughly 76 GB for an 8k context including KV cache and overhead. At 128k context the f16 KV cache alone is 24.7 GB.
Can I run GLM-4.5-Air on a RTX PRO 6000 96GB (bonus page)?
Yes: on RTX PRO 6000 96GB (bonus page) it fits fully as Q5_K_M at about 95 tok/s (estimated). 8 of 26 hardware configurations fit it fully at 16k context.
What is the maximum context for GLM-4.5-Air?
128k tokens natively. Memory, not the model, is usually the limit: see the KV cache table above.
All models: model index · by memory: 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · 48 GB · 64 GB · 96 GB · 128 GB · 192 GB · 256 GB · 512 GB. Numbers use the same fit math as the advisor; sources and methods.