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

Can Llama 4 Scout 17B 16E Instruct run on the H100 PCIe?

Yes. At 8K context the best fit is Q4_K_M, using about 65.2 GB of the 76.0 GB usable on the H100 PCIe. Estimated speed ceiling: ~178 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: Q4_K_M at 8K context then needs about 66.8 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)39.5 GB Fits40.2 GB Fits44.7 GB Fits62.7 GB Fits296
3-bit (Q3_K_M)51.0 GB Fits51.7 GB Fits56.2 GB Fits74.2 GB Tight227
4-bit (Q4_K_M) •64.4 GB Fits65.2 GB Fits69.7 GB Tight87.7 GB No178
5-bit (Q5_K_M)73.6 GB Tight74.4 GB Tight78.9 GB No96.9 GB No156
6-bit (Q6_K) •84.2 GB No85.0 GB No89.5 GB No107 GB No—
8-bit (Q8_0) •107 GB No108 GB No112 GB No130 GB No—
16-bit (F16/BF16)204 GB No205 GB No209 GB No227 GB No—

• real GGUF file size from lmstudio-community/Llama-4-Scout-17B-16E-Instruct-GGUF. Speed is a bandwidth ceiling (2000 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

Llama 4 Scout 17B 16E Instruct on every GPU and Mac · Every model that runs on the H100 PCIe · 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-4-Scout-17B-16E-Instruct), NVIDIA specs. Model data last checked 2026-11-18; refreshed hourly.