Nous Research · Propaganda-reduced fine-tune
Arete-27B
Nous Research has released Arete-27B, an Apache 2.0 fine-tune of Qwen3.8-27B. On Nous's own 803-prompt evaluation, propaganda answers fell from 22% to 0.9%, while the Hermes Bench score stayed flat at 65.60%.
Open the source ↗Similar Language Models releases
- Your algorithm
Meta (Engineering at Meta) · LLM Recommendation System · Week 47, 2026
- LLMON: LLM-Native Markup Language (Granite 4.1 LLMON previews)
IBM Granite (ibm-granite) · Structured Prompt Format · Week 47, 2026
- Kimi K3.1 Pro Highspeed
Moonshot AI, via AWS Machine Learning Blog · Agentic LLM on Bedrock · Week 47, 2026
- BotPsy-0.8B
Tether AI Research (QVAC) · On-Device Agent LLM · Week 47, 2026
- Muse Ember
Meta Superintelligence Labs · Lightweight agent model · Week 47, 2026
- qwenFS
vixhal-baraiya (GitHub) · Filesystem-in-Weights LLM · Week 47, 2026
More from Nous Research
- Hermes Agent
Nous Research · Agent Framework · Week 18, 2026
- Atropos
Nous Research · Evaluation & Benchmarks · Week 16, 2026
- Atropos
Nous Research · Agent Framework · Week 11, 2026
- NousCoder-14B
Nous Research · Code Generation · Week 2, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.