SmolLM2-360M-Instruct

Llama family · 0.4B params

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

What the SmolLM2-360M-Instruct numbers mean

The fastest verified result on our board is 968.1 output tok/s on an RTX PRO 6000 Blackwell at Q8_0 with a 4608-token context. That is about 1.0 ms per generated token — 500 tokens takes roughly 0.5 seconds. Prompt processing on the same record runs at 103783.1 tok/s, so a 2,000-token prompt is read in about 0.0 seconds. Peak VRAM was measured at 1.1 GB.

How much VRAM does SmolLM2-360M-Instruct need?

SmolLM2-360M-Instruct has 0.4B 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 SmolLM2-360M-Instruct's parameter count. Full benchmark board.

All benchmarks Methodology