LFM2.5-8B-A1B-8bit-XL-mlx

LFM2.5-8B-A1B 8-bit XL MLX

LFM2.5-8B-A1B by Liquid AI — a hybrid conv + attention MoE built for on-device deployment (extended pre-training + RL on the LFM2 architecture), quantized for Apple Silicon with the BaseQuant_XL 8-bit recipe.

8.3B total / 1.5B active parameters. Designed to power on-device personal assistants: chained tool calls, complex instruction following, agentic tasks — at a memory footprint that fits 16 GB Macs.

About XL Quantization

BaseQuant_XL is a fully data-agnostic, static quantization. No calibration dataset, no sensitivity analysis, no importance matrix. Precision is allocated purely by architectural role — routing-critical layers get higher precision, bulk expert parameters get lower precision. The result is a transparent, faithful capture of the source model.

Data-dependent calibration quantizations (iMatrix, AWQ, GPTQ, oQ, oQ4e, etc.) use a calibration set to guide bit allocation. This can produce a skewed representation of the model: domains well-represented in the calibration data (English, popular topics, public or leaked benchmarks) are preserved better, while underrepresented domains (non-English languages, niche use cases, your own data) are preserved worse. XL avoids this trade-off entirely — it generalizes honestly because it is never fit to any particular data distribution.

Quickstart

pip install -U mlx-lm
mlx_lm.chat --model leonsarmiento/LFM2.5-8B-A1B-8bit-XL-mlx

Thinking is native to LFM2.5 — reasoning traces are emitted inline in the response.

Quantization Strategy

• Bits per weight: 8.501 · Total size: ~9.0 GB (2 shards) · Group size: 64

Note: tie_word_embeddings=true — the 8-bit embedding doubles as the output head (same treatment as our Gemma 4 XL builds).

Liquid AI also publishes their own uniform 8-bit MLX build (LFM2.5-8B-A1B-MLX-8bit); this XL variant differs by keeping the router gate in bf16.

Recommended Inference Parameters

Per Liquid AI's model card / shipped generation_config.json:

Model Overview

Source Model Benchmarks (from Liquid AI)

Source

LiquidAI/LFM2.5-8B-A1B — Liquid AI docs