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
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 38.4 GB Fits | 39.1 GB Fits | 43.6 GB Fits | 61.6 GB Fits | 730 |
| 3-bit (Q3_K_M) • | 49.7 GB Fits | 50.5 GB Fits | 55.0 GB Fits | 73.0 GB Fits | 558 |
| 4-bit (Q4_K_M) • | 62.4 GB Fits | 63.2 GB Fits | 67.7 GB Fits | 85.7 GB Fits | 442 |
| 5-bit (Q5_K_M) • | 72.8 GB Fits | 73.6 GB Fits | 78.1 GB Fits | 96.1 GB Fits | 378 |
| 6-bit (Q6_K) • | 83.9 GB Fits | 84.6 GB Fits | 89.1 GB Fits | 107 GB Fits | 327 |
| 8-bit (Q8_0) • | 108 GB Fits | 109 GB Fits | 113 GB Fits | 131 GB Tight | 252 |
| 16-bit (F16/BF16) • | 202 GB No | 203 GB No | 208 GB No | 226 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
- Cheapest listed GPU that runs Llama 4 Scout 17B 16E Instruct: DGX Spark (128 GB, launch MSRP $3,999) at Q6_K, fully in VRAM at 8K context.
- Largest popular model that fits the H200: Qwen3.8 Flash Next (180B, MoE) at Q5_K_M, about 121 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 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.