cd/entity/qwen3:30b-a3b· home› entities› qwen3:30b-a3b
grep -l @qwen3:30b-a3b /news/*.json | wc -l → 1

qwen3:30b-a3b

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

01:01
2026-07-26
promptcube3.com
large-language-models

HotPin: Running 120B MoE on 24GB RAM

A new llama.cpp patch called HotPin enables running a 120-billion-parameter mixture-of-experts (MoE) model on just 24GB of RAM, achieving up to 67% memory savings and a 45% speedup over standard swapp…

// co-occurs with top 7 entities
llama.cpp 1 HotPin 1 AMD Ryzen AI 9 HX 370 1 gpt-oss:120b 1 gemma4:26b-a4b 1 GLM-4.7-Flash 1 LozzKappa 1
// topics top 3 topics
large language models 1 ai infrastructure 1 developer tools 1