LFM2-350M

LFM family · 0.3B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Sep 4, 2026. What these labels mean.

What the LFM2-350M numbers mean

The fastest result on our board is 2231.4 output tok/s on an RTX 5090 at NVFP4 with a 704-token context. That is about 0.4 ms per generated token — 500 tokens takes roughly 0.2 seconds. Peak VRAM was measured at 28.4 GB.

How much VRAM does LFM2-350M need?

LFM2-350M has 0.3B 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 LFM2-350M's parameter count. Full benchmark board.

All benchmarks Methodology