Can GLM 4.5 Air run on the 2x RTX 5090?
Yes. At 8K context the best fit is Q2_K, using about 44.3 GB of the 60.8 GB usable on the 2x RTX 5090. Estimated speed ceiling: ~292 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 43.6 GB Fits | 44.3 GB Fits | 48.6 GB Fits | 65.9 GB No | 292 |
| 3-bit (Q3_K_M) • | 54.7 GB Fits | 55.4 GB Tight | 59.7 GB Tight | 77.0 GB No | 231 |
| 4-bit (Q4_K_M) • | 69.4 GB No | 70.1 GB No | 74.4 GB No | 91.7 GB No | — |
| 5-bit (Q5_K_M) • | 79.2 GB No | 79.9 GB No | 84.2 GB No | 101 GB No | — |
| 6-bit (Q6_K) • | 93.6 GB No | 94.3 GB No | 98.6 GB No | 116 GB No | — |
| 8-bit (Q8_0) • | 111 GB No | 112 GB No | 116 GB No | 133 GB No | — |
| 16-bit (F16/BF16) • | 207 GB No | 208 GB No | 212 GB No | 230 GB No | — |
• real GGUF file size from unsloth/GLM-4.5-Air-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.
More
GLM 4.5 Air on every GPU and Mac · Every model that runs on the 2x RTX 5090 · Try other settings in the calculator
Data: Hugging Face Hub (zai-org/GLM-4.5-Air), NVIDIA specs. Data as of 2026-11-17.