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.
More from Models
- DeepSeek V4 on Cloudflare Workers AI: First 1M Token Context Models — ritakozlov · 2026-08-15
- Running LTX-2.5 on 8GB VRAM + 16GB RAM: A user's experience — Rique_Belt · 2026-08-15
- Dev Reports Better Performance with Qwen 3.8 Reasoning Disabled — Jordanthecomeback · 2026-08-15
- Kimi K3 Claims to Be Claude: Moonshot Faces Distillation Controversy — RageML · 2026-08-15
- Qwen 3.8 27B shows different rejection traits than Gemma4; plan to generate 10k prompts for analysis — max_paperclips · 2026-08-15
- Qwen 3.8-27B model praised for strong performance — remilouf · 2026-08-15