LiquidAI releases QAD checkpoints, 4-bit models retain 97% BF16 accuracy
JosephJacks_ · x · 2026-08-20
LiquidAI has released updated 4-bit checkpoints for the LFM2.5 series, trained with Quantization-Aware Distillation (QAD).
- Performance: The checkpoints recover accuracy lost to 4-bit quantization, reaching roughly 97% of their BF16 averages while retaining low memory footprint and high throughput.
- Usage: A developer shared a command to run the 2.6B model via llama-server with specific parameters (131k context, temp 0.1, top-k 50), noting impressive performance on minimal hardware.
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