Skip to content

Head-to-head · LFM

LFM3-1.7B vs LFM2.5 8B-A1B

LFM3-1.7B needs ~2.1 GB at Q4_K_M; LFM2.5 8B-A1B needs ~6.3 GB. That ~4.2 GB gap decides which hardware runs each; they differ on 2 of the 13 devices below.

Spec LFM3-1.7B LFM2.5 8B-A1B
Parameters1.73B8.3B MoE
Memory at Q4_K_M~2.1 GB~6.3 GB
Context window256k128k
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 LFM3-1.7B LFM2.5 8B-A1B
Q2_K 0.7 GB* 3.5 GB*
Q3_K_M 0.8 GB* 4.1 GB*
Q4_K_M 1.02 GB 4.8 GB
Q5_K_M 1.2 GB* 5.9 GB*
Q6_K 1.4 GB* 6.8 GB*
Q8_0 1.72 GB 8.39 GB
FP16 3.23 GB 15.78 GB

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

Bottom line

The larger LFM2.5 8B-A1B needs ~6.3 GB; LFM3-1.7B runs on lighter hardware at ~2.1 GB with more headroom and faster responses. Check each against your exact device: what runs LFM3-1.7B · what runs LFM2.5 8B-A1B.

More LFM comparisons

FAQ

What is the difference in memory between LFM3-1.7B and LFM2.5 8B-A1B?

At Q4_K_M, LFM3-1.7B needs about 2.1 GB and LFM2.5 8B-A1B needs about 6.3 GB, a difference of ~4.2 GB.

Should I run LFM3-1.7B or LFM2.5 8B-A1B?

Run LFM2.5 8B-A1B if your hardware has the ~6.3 GB it needs and you want maximum quality; run LFM3-1.7B (~2.1 GB) for lighter hardware, faster responses, and more memory headroom.

Full breakdowns: LFM3-1.7B · LFM2.5 8B-A1B · all models × devices.

Sources

Memory figures are estimates at Q4_K_M. Catalog updated 2026-11-01. See methodology.