Developing story · 2 episodes · 25 Oct to 6 Nov

Bartowski releases Xing4.0-29B-A4B quantized models for llama.cpp

Quantized versions of large models like this enable developers and hobbyists to run advanced AI locally without high-end hardware. The speculative decoding and imatrix optimizations could improve inference speed for text generation tasks, making powerful models more accessible for research and small-scale applications.

Fri 6 Nov

Researchnew

Bartowski releases Xing4.0-29B-A4B quantized models for llama.cpp

A user named bartowski has shared quantized versions of the Xing4.0-29B-A4B model on Hugging Face, optimized for llama.cpp with speculative decoding and imatrix calibration. The original model has…

1 source primary source
Sun 25 Oct

Researchnew

MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model

MarkTechPost published a technical tutorial demonstrating how to run Underdog Saluki 27B, a 7.9 GB quantized version of Qwen3.8-27B that claims to preserve tool-calling ability at roughly two bits…

1 source

Who and what

Bartowski releases Xing4.0-29B-A4B quantized models for llama.cpp

MarkTechPost publishes tutorial on running Underdog Saluki 27B quantized model