RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM 4.7 Flash run on the RTX 6000 Ada?

Yes. At 8K context the best fit is Q8_0, using about 30.8 GB of the 45.6 GB usable on the RTX 6000 Ada. Estimated speed ceiling: ~204 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •11.5 GB Fits11.7 GB Fits12.9 GB Fits17.9 GB Fits573
3-bit (Q3_K_M) •14.5 GB Fits14.7 GB Fits16.0 GB Fits20.9 GB Fits445
4-bit (Q4_K_M) •18.0 GB Fits18.2 GB Fits19.4 GB Fits24.4 GB Fits355
5-bit (Q5_K_M) •20.8 GB Fits21.0 GB Fits22.3 GB Fits27.2 GB Fits304
6-bit (Q6_K) •23.9 GB Fits24.1 GB Fits25.3 GB Fits30.3 GB Fits263
8-bit (Q8_0) •30.6 GB Fits30.8 GB Fits32.0 GB Fits37.0 GB Fits204
16-bit (F16/BF16) •56.7 GB No56.9 GB No58.1 GB No63.1 GB No—

• real GGUF file size from unsloth/GLM-4.7-Flash-GGUF. Speed is a bandwidth ceiling (960 GB/s), not a benchmark. Methodology.

More

GLM 4.7 Flash on every GPU and Mac · Every model that runs on the RTX 6000 Ada · Other models that fit 48 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/GLM-4.7-Flash), NVIDIA specs. Data as of 2026-11-17.