SmolLM2-135M-Instruct

Llama family · 0.1B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 17, 2026. What these labels mean.

What the SmolLM2-135M-Instruct numbers mean

The fastest result on our board is 1102.1 output tok/s on an RTX 5090 at Q2_K with a 2048-token context. That is about 0.9 ms per generated token — 500 tokens takes roughly 0.5 seconds. Prompt processing on the same record runs at 75749.0 tok/s, so a 2,000-token prompt is read in about 0.0 seconds.

How much VRAM does SmolLM2-135M-Instruct need?

SmolLM2-135M-Instruct has 0.1B 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 SmolLM2-135M-Instruct's parameter count. Full benchmark board.

All benchmarks Methodology