RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM 4 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 axteam/GLM-4-32B-0414-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

GLM 4 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-4-32B-0414), NVIDIA specs. Data as of 2026-11-17.