view post Post 5264 Qwen3.6-27B is out now! Run it locally on 18GB RAM. 💜Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.GGUFs to run: unsloth/Qwen3.6-27B-GGUFGuide + MLX: https://unsloth.ai/docs/models/qwen3.6 See translation 🔥 28 28 + Reply
LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models Paper • 2310.08659 • Published Oct 12, 2023 • 29
Transformers.js V4 demos Collection A collection of demos built with Transformers.js V4 • 24 items • Updated 19 days ago • 58
view article Article A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes Aug 17, 2022 • 131
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 Feb 20 • 505
view article Article I Let a Lobster Run My Jetson: What OpenClaw Taught Me About the Future of Computing Feb 19 • 16
view article Article From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output Feb 7 • 22
Beyond Transcription: Mechanistic Interpretability in ASR Paper • 2508.15882 • Published Aug 21, 2025 • 89