Unsloth Releases Qwen2.5-72B Quants: 1-bit Version Runs on 8GB RAM
cephaloform · x · 2026-08-20
Unsloth AI has released new GGUF quantizations for Qwen2.5-72B. The Dynamic V3 version achieves >10% higher accuracy on benchmarks like Div-300 and KLD. Notably, they also released a 1-bit extreme quantization that runs on just 8GB RAM while retaining approximately 77% of BF16 accuracy.
More from Infra
- 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
- Samsung cuts Q4 phone output as Nittobo shifts E-glass to AI-chip T-glass — zephyr_z9 · 2026-10-16
- White House AI chief discusses Empire AI, New York's shared compute infrastructure — mkratsios47 · 2026-10-16