RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can GLM 4.6V run on the H100 SXM?

Yes. At 8K context the best fit is Q3_K_M, using about 52.2 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~470 tokens/sec.

+ 1.6 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q3_K_M at 8K context then needs about 53.8 GB (still fits). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •43.0 GB Fits43.8 GB Fits48.1 GB Fits65.3 GB Fits565
3-bit (Q3_K_M) •51.5 GB Fits52.2 GB Fits56.6 GB Fits73.8 GB Tight470
4-bit (Q4_K_M) •67.9 GB Fits68.6 GB Tight72.9 GB Tight90.1 GB No354
5-bit (Q5_K_M) •77.0 GB No77.7 GB No82.0 GB No99.3 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)202 GB No203 GB No207 GB No224 GB No—

• real GGUF file size from bartowski/zai-org_GLM-4.6V-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

GLM 4.6V on every GPU and Mac · Every model that runs on the H100 SXM · Other models that fit 64 GB VRAM · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (zai-org/GLM-4.6V), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.