Can GLM 4.6 run on the RTX 4070 Ti Super?
No. Even at 2-bit with 8K context, GLM 4.6 needs about 125 GB, more than the 15.2 GB usable on the RTX 4070 Ti Super.
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 | 125 GB No | 134 GB No | 168 GB No | — |
| 3-bit (Q3_K_M) • | 161 GB No | 162 GB No | 171 GB No | 206 GB No | — |
| 4-bit (Q4_K_M) • | 203 GB No | 204 GB No | 213 GB No | 247 GB No | — |
| 5-bit (Q5_K_M) • | 238 GB No | 239 GB No | 248 GB No | 282 GB No | — |
| 6-bit (Q6_K) • | 275 GB No | 277 GB No | 285 GB No | 320 GB No | — |
| 8-bit (Q8_0) • | 355 GB No | 357 GB No | 365 GB No | 400 GB No | — |
| 16-bit (F16/BF16) • | 667 GB No | 668 GB No | 677 GB No | 711 GB No | — |
• real GGUF file size from unsloth/GLM-4.6-GGUF. Speed is a bandwidth ceiling (672 GB/s), not a benchmark. Methodology.
Hardware that does fit it
H200Mac M2 Ultra 192GBMac M3 Ultra 256GBMac M3 Ultra 512GB
More
GLM 4.6 on every GPU and Mac · Every model that runs on the RTX 4070 Ti Super · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (zai-org/GLM-4.6), NVIDIA specs. Data as of 2026-11-17.