# Liquid AI — LFM2.5 Q4_0: Quantization-Aware Distillation for Edge Deployment

- Company: Liquid AI (liquid.ai)
- Announced: 2026-08-19
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.liquid.ai/blog/qad
- Record: https://forck.live/items/16772-lfm2-5-q4-0-quantization-aware-distillation-for-edge-deployment
- Subject: LFM / d1 models

Today, we release updated 4-bit checkpoints for LFM2.5-230M, LFM2.5-350M, LFM2.5-1.2B-Instruct, and LFM2.5-2.6B trained with Quantization-Aware Distillation (QAD) . QAD is a technique to distill a high-precision teacher model into a quantized student model. These checkpoints keep the low memory footprint and high throughput of Q4_0 GGUFs while recovering most of the accuracy lost to quantization: all four land at roughly 97% of their BF16 averages. The QAD GGUFs are available today on Hugging Face: LFM2.5-230M , LFM2.5-350M , LFM2.5-1.2B-Instruct , and LFM2.5-2.6B . Benchmarks For all four models, we compare their released GGUFs produced with post-training quantization (PTQ) against the trained QAD Q4_0 checkpoints on a benchmark suite spanning reasoning, instruction-following, tool use, and agentic capabilities: GPQA Diamond, MMLU-Pro, IFEval, IFBench, Multi-IF, and BFCLv4. The BF16 GGUF serves as the in-format ceiling. We also add one scale-appropriate math evaluation: GSM8K for LFM2.5-230M and LFM2.5-350M, and AIME25 for LFM2.5-1.2B-Instruct and LFM2.5-2.6B. We report the mean across five repeats. …

---

Record: https://forck.live/items/16772-lfm2-5-q4-0-quantization-aware-distillation-for-edge-deployment
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md