Local Ai
From the @HamsterResearch lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-nat…
From the @HamsterResearch lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-native 4-bit 60% smaller than stock q4 - Pruned 512→288 experts
From the @HamsterResearch lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-native 4-bit 60% smaller than stock q4 - Pruned 512→288 experts via REAP - 91.5% HumanEval (vs 93.9% stock) @huggingface links below ↓ Media
Related
- We just shipped a full revamp of the RunAnywhere apps. iOS and Android, live now. One assistant, fully on-device, works offline: - new UI, o…
- What options exist for running the largest local models at full precision?
Source: Yohei Nakajima (X) | 2026-08-28