← Back to Model Beat
Models·Aug 16·all news from August 16, 2026

Trying out local AI: This is what Qwen3.8-27B can do

Trying out local AI: This is what Qwen3.8-27B can do heise online

ModelsQwen3.8 27B

Covered by 1 source

Related stories

ModelsMemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M ReaderOct 6ModelsPrismML Releases Ternary Bonsai 2 27B: A 5.9 GB Apache 2.0 Model Retaining 98.2% of Qwen3.8 27B PerformanceSep 18ModelsAlibaba's Qwen 3.8 27B Rivals Opus 4.6 for Free LocallyAug 17 · 3 sourcesModelsQwen 3.8 27B Hits 17.1 Tokens per Second with MTP ToggleSep 10