RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM Z1 32B 0414 run on the H200?

Yes. At 8K context the best fit is F16, using about 61.8 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~74 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •12.4 GB Fits12.6 GB Fits14.0 GB Fits390
3-bit (Q3_K_M) •15.7 GB Fits16.0 GB Fits17.4 GB Fits302
4-bit (Q4_K_M) •19.3 GB Fits19.5 GB Fits20.9 GB Fits244
5-bit (Q5_K_M) •22.4 GB Fits22.7 GB Fits24.1 GB Fits208
6-bit (Q6_K) •25.8 GB Fits26.1 GB Fits27.5 GB Fits180
8-bit (Q8_0) •33.2 GB Fits33.4 GB Fits34.8 GB Fits139
16-bit (F16/BF16) •61.6 GB Fits61.8 GB Fits63.3 GB Fits74

• real GGUF file size from unsloth/GLM-Z1-32B-0414-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

GLM Z1 32B 0414 on every GPU and Mac · Every model that runs on the H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (zai-org/GLM-Z1-32B-0414), NVIDIA specs. Data as of 2026-11-17.