Can GLM 4.7 run on the 2x RTX 4090?
No. Even at 2-bit with 8K context, GLM 4.7 needs about 126 GB, more than the 45.6 GB usable on the 2x RTX 4090.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 124 GB No | 126 GB No | 134 GB No | 169 GB No | — |
| 3-bit (Q3_K_M) • | 162 GB No | 163 GB No | 172 GB No | 206 GB No | — |
| 4-bit (Q4_K_M) • | 204 GB No | 205 GB No | 214 GB No | 248 GB No | — |
| 5-bit (Q5_K_M) • | 239 GB No | 240 GB No | 249 GB No | 283 GB No | — |
| 6-bit (Q6_K) • | 276 GB No | 278 GB No | 286 GB No | 321 GB No | — |
| 8-bit (Q8_0) • | 357 GB No | 358 GB No | 367 GB No | 401 GB No | — |
| 16-bit (F16/BF16) • | 670 GB No | 671 GB No | 680 GB No | 714 GB No | — |
• real GGUF file size from unsloth/GLM-4.7-GGUF. Speed is a bandwidth ceiling (1008 GB/s), not a benchmark. Methodology.
Hardware that does fit it
H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
More
GLM 4.7 on every GPU and Mac · Every model that runs on the 2x RTX 4090 · Try other settings in the calculator
Data: Hugging Face Hub (zai-org/GLM-4.7), NVIDIA specs. Data as of 2026-11-17.