@hank_aibtc: Family, local LLMs are incredibly impressive! I stumbled upon this gpt-oss-20b-tq3 on Hugging Face, and it's truly captivating! OpenAI's official open-source 20B+ parameter MoE model, optimized by the community using TurboQuant 3-bit quantization + MLX...
Summary
The article highlights the gpt-oss-20b-tq3 model, a quantized version of an OpenAI MoE model that runs efficiently on standard 16GB MacBook Airs using TurboQuant and MLX optimizations.
Similar Articles
@DivyanshT91162: Local LLMs just hit a whole new level This Hugging Face release is actually insane: "gpt-oss-20b-tq3" An official 20B+ …
A new 20B+ parameter MoE model from OpenAI, quantized to 3-bit via TurboQuant and optimized with MLX, allows for high-performance local LLM inference on standard 16GB MacBooks.
@witcheer: can’t believe gpt-oss-20b perfs on 8GB vRAM 21B total params, 3.6B active (MoE). OpenAI, Apache 2.0. uses only 1.8 GB V…
A new open-source MoE model, gpt-oss-20b (21B total, 3.6B active), runs on only 1.8GB VRAM and achieves perfect scores on agentic coding tasks, outperforming other local models like Gemma and Qwen.
@cuisitekp: A 9B model outperforms models several times larger. The team behind OLMo/Tülu from Ai2 and the University of Washington released a new paper called Tmax, claiming it's the strongest open-source RL training recipe for 'terminal agents'. Result: A 9B model on Terminal-Be…
Ai2 and the University of Washington released a paper titled Tmax, proposing the strongest open-source terminal agent RL training recipe to date. A 9B parameter model outperforms larger models on Terminal-Bench 2.0, with the key being low-cost generation of vast amounts of verifiable training data, not model size or algorithm.
@lucastech: really cool to see how much different gpt-oss-20b is compared to all other models I've tested, each quantization is dra…
GPT-OSS-20B model shows significant improvements in intelligence across quantizations while maintaining similar size, unlike other models.
@tom_doerr: Runs 35B models on 16GB RAM Macs https://github.com/walter-grace/mac-code…
A tool that enables running large language models like Qwen3.5-35B on 16GB Macs by streaming model weights from SSD, achieving up to 30 tok/s with an optimal configuration.