Llama-4-Scout-17B-16E-Instruct

Llama family · 109.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Sep 4, 2026. What these labels mean.

What the Llama-4-Scout-17B-16E-Instruct numbers mean

The fastest verified result on our board is 44.5 output tok/s on an CMP 170HX at UD-Q3_K_XL with a 2048-token context. That is about 22.5 ms per generated token — 500 tokens takes roughly 11.2 seconds. Prompt processing on the same record runs at 584.4 tok/s, so a 2,000-token prompt is read in about 3.4 seconds. Peak VRAM was measured at 46.6 GB.

How much VRAM does Llama-4-Scout-17B-16E-Instruct need?

Llama-4-Scout-17B-16E-Instruct has 109.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from Llama-4-Scout-17B-16E-Instruct's parameter count. Full benchmark board.

All benchmarks Methodology