RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Llama 4 Scout 17B 16E Instruct run on the H200?

Yes. At 8K context the best fit is Q8_0, using about 109 GB of the 134 GB usable on the H200. Estimated speed ceiling: ~252 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •38.4 GB Fits39.1 GB Fits43.6 GB Fits61.6 GB Fits730
3-bit (Q3_K_M) •49.7 GB Fits50.5 GB Fits55.0 GB Fits73.0 GB Fits558
4-bit (Q4_K_M) •62.4 GB Fits63.2 GB Fits67.7 GB Fits85.7 GB Fits442
5-bit (Q5_K_M) •72.8 GB Fits73.6 GB Fits78.1 GB Fits96.1 GB Fits378
6-bit (Q6_K) •83.9 GB Fits84.6 GB Fits89.1 GB Fits107 GB Fits327
8-bit (Q8_0) •108 GB Fits109 GB Fits113 GB Fits131 GB Tight252
16-bit (F16/BF16) •202 GB No203 GB No208 GB No226 GB No—

• real GGUF file size from unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF. Speed is a bandwidth ceiling (4800 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 H200 · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (meta-llama/Llama-4-Scout-17B-16E-Instruct), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.