Can Llama 3.2 11B Vision Instruct run on the H100 SXM?
Yes. At 8K context the best fit is F16, using about 20.1 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~171 tokens/sec.
+ 1.8 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: F16 at 8K context then needs about 21.9 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) | 5.0 GB Fits | 5.6 GB Fits | 9.4 GB Fits | 24.4 GB Fits | 837 |
| 3-bit (Q3_K_M) | 6.1 GB Fits | 6.8 GB Fits | 10.5 GB Fits | 25.5 GB Fits | 642 |
| 4-bit (Q4_K_M) • | 6.8 GB Fits | 7.4 GB Fits | 11.2 GB Fits | 26.2 GB Fits | 562 |
| 5-bit (Q5_K_M) | 8.4 GB Fits | 9.0 GB Fits | 12.7 GB Fits | 27.7 GB Fits | 441 |
| 6-bit (Q6_K) | 9.4 GB Fits | 10.0 GB Fits | 13.8 GB Fits | 28.8 GB Fits | 383 |
| 8-bit (Q8_0) • | 11.0 GB Fits | 11.6 GB Fits | 15.3 GB Fits | 30.3 GB Fits | 322 |
| 16-bit (F16/BF16) • | 19.5 GB Fits | 20.1 GB Fits | 23.9 GB Fits | 38.9 GB Fits | 171 |
• real GGUF file size from leafspark/Llama-3.2-11B-Vision-Instruct-GGUF. Speed is a bandwidth ceiling (3350 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs Llama 3.2 11B Vision Instruct: Arc B580 (12 GB, launch MSRP $249) 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
Llama 3.2 11B Vision Instruct 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 (meta-llama/Llama-3.2-11B-Vision-Instruct), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.