Liquid releases QAD quantized models, recovering 97% accuracy at 4-bit
helloiamleonie · x · 2026-08-19
Liquid AI released new 4-bit checkpoints trained with Quantization-Aware Distillation (QAD) for the LFM2.5 series (230M to 2.6B).
Technical Details:
- QAD distills a high-precision teacher model into a quantized student model to recover accuracy lost during quantization.
- Maintains the low memory footprint and high decode throughput of the Q40 format.
- All four checkpoints reach roughly 97% of their BF16 averages.
Developers can replace existing Q40 GGUFs directly for improved performance.
Related event: Liquid AI's QAD Delivers 4-bit Models Retaining 97% Performance(4 posts)→
More from Infra
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Microsoft Research unveils Magnetar, the fastest zkVM at 10-39x speedups and post-quantum security — jedisct1 · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16