Can GLM 4.5V run on the H100 SXM?
Yes. At 8K context the best fit is Q4_K_M, using about 61.4 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~397 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 39.0 GB Fits | 39.7 GB Fits | 44.1 GB Fits | 625 |
| 3-bit (Q3_K_M) | 50.4 GB Fits | 51.2 GB Fits | 55.5 GB Fits | 480 |
| 4-bit (Q4_K_M) • | 60.7 GB Fits | 61.4 GB Fits | 65.7 GB Fits | 397 |
| 5-bit (Q5_K_M) | 72.9 GB Tight | 73.6 GB Tight | 77.9 GB No | 329 |
| 6-bit (Q6_K) | 83.7 GB No | 84.4 GB No | 88.7 GB No | — |
| 8-bit (Q8_0) • | 107 GB No | 108 GB No | 112 GB No | — |
| 16-bit (F16/BF16) | 202 GB No | 203 GB No | 207 GB No | — |
• real GGUF file size from ggml-org/GLM-4.5V-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs GLM 4.5V: 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 4.5V 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-4.5V), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.