RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM 4.5V run on the RTX 4070?

No. Even at 2-bit with 8K context, GLM 4.5V needs about 39.7 GB, more than the 11.4 GB usable on the RTX 4070.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)39.0 GB No39.7 GB No44.1 GB No—
3-bit (Q3_K_M)50.4 GB No51.2 GB No55.5 GB No—
4-bit (Q4_K_M) •60.7 GB No61.4 GB No65.7 GB No—
5-bit (Q5_K_M)72.9 GB No73.6 GB No77.9 GB No—
6-bit (Q6_K)83.7 GB No84.4 GB No88.7 GB No—
8-bit (Q8_0) •107 GB No108 GB No112 GB No—
16-bit (F16/BF16)202 GB No203 GB No207 GB No—

• real GGUF file size from ggml-org/GLM-4.5V-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.

Hardware that does fit it

RTX A6000RTX 6000 AdaL40SMac M4 Pro 64GBMac M1 Max 64GBMac M4 Max 64GB

More

GLM 4.5V on every GPU and Mac · Every model that runs on the RTX 4070 · Other models that fit 12 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/GLM-4.5V), NVIDIA specs. Data as of 2026-11-17.