Qwen3.8 27B matches Opus 4.6 at home, running on MacBooks and RTX cards
daniel_mac8 · x · 2026-08-15
The Qwen3.8 27B model can be run locally with performance comparable to Opus 4.6.
Supported Hardware:
- MacBook M4 Pro or later with > 36GB RAM
- NVIDIA DGX Spark
- Single NVIDIA RTX GPU
All configurations work well, especially with quantized versions. The author runs it on a DGX Spark within prime-agent, noting that achieving this level of performance for just the cost of electricity is incredible.
Related event: Qwen2.5 Local Performance Review(2 posts)→
More from Models
- Prediction: frontier AI revenue growth could slow even as AI usage keeps rising — yi111 · 2026-10-16
- Meta teased 816B-param open-weight Muse Spark Open with 1M context, says meme thread — alexandr_wang · 2026-10-16
- Nolla Health Post-Trains Nemotron 3.5 VL: Visual Diagnosis Jumps from 35% to 66.8% — LoganGrasby · 2026-10-16
- Dev argues coding models now beat nearly all engineers in every branch of software — zack_overflow · 2026-10-16
- Prediction: Chinese frontier models could match GPT-6 by March 2027 — teortaxesTex · 2026-10-16
- Liquid AI's d1-ultra, #1 on Artificial Analysis Decision Index, lands on Vercel — JosephJacks_ · 2026-10-16