LFM2.5-2.6B

Llama family · 3.0B params

Evidence: 2 sourced runs · 1 independent source · first recorded Aug 26, 2026 · last recorded Sep 4, 2026. What these labels mean.

What the LFM2.5-2.6B numbers mean

The fastest verified result on our board is 305.6 output tok/s on an RTX 3090 at Q4_K_M with a 24576-token context. That is about 3.3 ms per generated token — 500 tokens takes roughly 1.6 seconds. Prompt processing on the same record runs at 7609.8 tok/s, so a 2,000-token prompt is read in about 0.3 seconds. Peak VRAM was measured at 2.3 GB. Across the 2 records we hold for this model the range is 132.4–305.6 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does LFM2.5-2.6B need?

LFM2.5-2.6B has 3.0B 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 LFM2.5-2.6B's parameter count. Full benchmark board.

All benchmarks Methodology