Qwen 3.8 27B vs Claude Fable 5.2: a $0 local model (65 vs 20 on AA Index) and which jobs it can take over
alex_verem · x · 2026-11-17
Anthropic's Claude Fable 5.2 (Nov 9, $8/$40 per million in/out tokens, 1M context) is the strongest closed model; Alibaba's Apache 2.0 Qwen 3.8 27B (Aug) runs free on your own machine. The article compares them: 65 vs 20 on Artificial Analysis Index v5.0.1, 1M vs 262K (extendable to 1M) tokens read at once, data sent to Anthropic vs staying local, 24GB Mac or 16GB GPU suffices. It also lays out a six-step private benchmark you can finish in an afternoon: list paid AI jobs, write 15 real tasks with pass marks, run them on both models via LM Studio/Ollama, score blind, and migrate the tasks Qwen passes to your computer.
More from Models
- Dev praises Gemini 4 carbon as his favorite model despite 20-minute waits — willcb · 2026-11-17
- Blogger finds Astra skips steps on research tasks while carbon dutifully finishes them — lxfater · 2026-11-17
- Reuters exclusive: China taps US AI models via distillation to train homegrown rivals — ns123abc · 2026-11-17
- IFM releases K2-Horizon: six fully open LLMs up to 375B MoE, trained on ~10T synthetic tokens — IFM · 2026-11-17
- Optimization researcher: Astra proved with one prompt what we couldn't — bremen79 · 2026-11-17
- Gemini's AI Overview caught fabricating brake rotor dimensions for a Fisker Ocean query — AWTom · 2026-11-17