LFM2-24B-A2B

Llama family · 24.0B params

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

What the LFM2-24B-A2B numbers mean

The fastest result on our board is 393.2 output tok/s on an RTX 5090 at Q4_K_M with a 2048-token context. That is about 2.5 ms per generated token — 500 tokens takes roughly 1.3 seconds. Prompt processing on the same record runs at 1718.2 tok/s, so a 2,000-token prompt is read in about 1.2 seconds.

How much VRAM does LFM2-24B-A2B need?

LFM2-24B-A2B has 24.0B 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 LFM2-24B-A2B's parameter count. Full benchmark board.

All benchmarks Methodology