RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can GLM 4.6 run on the H200?

Yes. At 8K context the best fit is Q2_K, using about 125 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~385 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •124 GB Tight125 GB Tight134 GB Tight168 GB No385
3-bit (Q3_K_M) •161 GB No162 GB No171 GB No206 GB No—
4-bit (Q4_K_M) •203 GB No204 GB No213 GB No247 GB No—
5-bit (Q5_K_M) •238 GB No239 GB No248 GB No282 GB No—
6-bit (Q6_K) •275 GB No277 GB No285 GB No320 GB No—
8-bit (Q8_0) •355 GB No357 GB No365 GB No400 GB No—
16-bit (F16/BF16) •667 GB No668 GB No677 GB No711 GB No—

• real GGUF file size from unsloth/GLM-4.6-GGUF. Speed is a bandwidth ceiling (4800 GB/s), not a benchmark. Methodology.

More

GLM 4.6 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-4.6), NVIDIA specs. Data as of 2026-11-17.