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

Can Unlimited OCR 2 run on the H100 SXM?

Yes. At 8K context the best fit is F16, using about 6.6 GB of the 76.0 GB usable on the H100 SXM. Estimated speed ceiling: ~1657 tokens/sec.

+ 0.8 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 7.4 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)2.0 GB Fits2.3 GB Fits3.7 GB Fits9.3 GB Fits7776
3-bit (Q3_K_M)2.4 GB Fits2.6 GB Fits4.0 GB Fits9.7 GB Fits5966
4-bit (Q4_K_M)2.8 GB Fits3.0 GB Fits4.4 GB Fits10.1 GB Fits4770
5-bit (Q5_K_M)3.1 GB Fits3.3 GB Fits4.7 GB Fits10.4 GB Fits4093
6-bit (Q6_K) •3.4 GB Fits3.7 GB Fits5.1 GB Fits10.7 GB Fits3555
8-bit (Q8_0) •3.8 GB Fits4.0 GB Fits5.4 GB Fits11.1 GB Fits3111
16-bit (F16/BF16) •6.4 GB Fits6.6 GB Fits8.0 GB Fits13.6 GB Fits1657

• real GGUF file size from AtomicChat/Unlimited-OCR-2-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

Unlimited OCR 2 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 (baidu/Unlimited-OCR-2), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.