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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 43.0 GB Fits | 43.8 GB Fits | 48.1 GB Fits | 65.3 GB Fits | 565 |
| 3-bit (Q3_K_M) • | 51.5 GB Fits | 52.2 GB Fits | 56.6 GB Fits | 73.8 GB Tight | 470 |
| 4-bit (Q4_K_M) • | 67.9 GB Fits | 68.6 GB Tight | 72.9 GB Tight | 90.1 GB No | 354 |
| 5-bit (Q5_K_M) • | 77.0 GB No | 77.7 GB No | 82.0 GB No | 99.3 GB No | — |
| 6-bit (Q6_K) • | 90.7 GB No | 91.4 GB No | 95.7 GB No | 113 GB No | — |
| 8-bit (Q8_0) • | 107 GB No | 108 GB No | 112 GB No | 129 GB No | — |
| 16-bit (F16/BF16) | 202 GB No | 203 GB No | 207 GB No | 224 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
- Cheapest listed GPU that runs GLM 4.6V: DGX Spark (128 GB, launch MSRP $3,999) at Q6_K, fully in VRAM at 8K context.
- Largest popular model that fits the H100 SXM: gpt-oss 120B (117B, MoE) at F16, about 61.9 GB at 8K context.
"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.