Skip to content

Head-to-head · LFM

LFM2.5 8B-A1B vs LFM2 24B-A2B

LFM2.5 8B-A1B needs ~6.7 GB at Q4_K_M; LFM2 24B-A2B needs ~15.4 GB. That ~8.7 GB gap decides which hardware runs each; they differ on 6 of the 14 devices below.

Spec LFM2.5 8B-A1B LFM2 24B-A2B
Parameters8.3B MoE24B MoE
Memory at Q4_K_M~6.7 GB~15.4 GB
Context window128k32k
LMArenanot rankednot ranked
LicenseLFM Open License v1.0LFM Open License v1.0

Which devices run each

A representative spread across the memory range. Tap a verdict for the full breakdown.

Size at each quantization

Quant LFM2.5 8B-A1B LFM2 24B-A2B
Q2_K 3.5 GB* 10.1 GB*
Q3_K_M 4.1 GB* 11.7 GB*
Q4_K_M 5.2 GB 13.43 GB
Q5_K_M 5.9 GB* 17.1 GB*
Q6_K 6.8 GB* 19.7 GB*
Q8_0 9 GB 23.61 GB
FP16 17 GB 44.42 GB

* derived from bits-per-weight; unstarred sizes are measured GGUF files.

Bottom line

The larger LFM2 24B-A2B needs ~15.4 GB; LFM2.5 8B-A1B runs on lighter hardware at ~6.7 GB with more headroom and faster responses. Check each against your exact device: what runs LFM2.5 8B-A1B · what runs LFM2 24B-A2B.

More LFM comparisons

FAQ

What is the difference in memory between LFM2.5 8B-A1B and LFM2 24B-A2B?

At Q4_K_M, LFM2.5 8B-A1B needs about 6.7 GB and LFM2 24B-A2B needs about 15.4 GB, a difference of ~8.7 GB.

Should I run LFM2.5 8B-A1B or LFM2 24B-A2B?

Run LFM2 24B-A2B if your hardware has the ~15.4 GB it needs and you want maximum quality; run LFM2.5 8B-A1B (~6.7 GB) for lighter hardware, faster responses, and more memory headroom.

Full breakdowns: LFM2.5 8B-A1B · LFM2 24B-A2B · all models × devices.

Sources

Memory figures are estimates at Q4_K_M, validated 2026-08-03. See methodology.