←Back to NewsAI News/LlmsmodelLlmsPost TrainingDavidAU's Qwen3.8 Fine-Tune Beats the Base Model at a Tenth of Thinking TokensA community fine-tune of Qwen3.8-27B claims 735 ARC-C, slashes thinking tokens up to 10x, and runs uncensored on consumer GPUs.SourceAlphaSignalPublishedSep 1, 2026, 7:01 AMAuthorAlphaSignal NewsroomRead1 min readA community fine-tune of Qwen3.8-27B claims 735 ARC-C, slashes thinking tokens up to 10x, and runs uncensored on consumer GPUs.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsMultiverse Computing · newsMultiverse Computing's Quasar 1.1 Uses Quantum Data to Shrink a 438B Modelhumans& · newshumans&'s Persimmon Fools AI Detectors at Human Rates With 550B ParametersAlphaSignal · modelUkisAI's Swift-Qwen3.8 Slashes AI Reasoning Tokens by 58% With Almost No Accuracy Loss
