RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM 4.6V run on the RTX 5090?

No. Even at 2-bit with 8K context, GLM 4.6V needs about 43.0 GB, more than the 30.4 GB usable on the RTX 5090.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •42.3 GB No43.0 GB No47.3 GB No64.5 GB No—
3-bit (Q3_K_M) •53.0 GB No53.8 GB No58.1 GB No75.3 GB No—
4-bit (Q4_K_M) •67.1 GB No67.8 GB No72.2 GB No89.4 GB No—
5-bit (Q5_K_M) •76.6 GB No77.3 GB No81.6 GB No98.9 GB No—
6-bit (Q6_K) •90.7 GB No91.4 GB No95.7 GB No113 GB No—
8-bit (Q8_0) •107 GB No108 GB No112 GB No129 GB No—
16-bit (F16/BF16) •200 GB No201 GB No206 GB No223 GB No—

• real GGUF file size from unsloth/GLM-4.6V-GGUF. Speed is a bandwidth ceiling (1792 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 4.6V on every GPU and Mac · Every model that runs on the RTX 5090 · Other models that fit 32 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/GLM-4.6V), NVIDIA specs. Data as of 2026-11-17.