Qwen3.6-27B
Alibaba's Qwen3.6-27B is a 27-billion-parameter AI model optimized for flagship-level coding performance and efficient local deployment through quantization.
Signal Radar
Five-axis snapshot of this entity's footprint
Mentions × Lab Attention
Weekly mentions (solid) and average article relevance (dotted)
Timeline
2- Research MilestoneMay 15, 2026
Qwen 3.6 27B achieves 34 tok/s on M5 Max MacBook Pro with 90% acceptance rate
View source- performance:
- 34 tok/s
- acceptance rate:
- 90%
- Research MilestoneApr 22, 2026
Achieved flagship-level coding performance, surpassing the larger Qwen3.5-397B-A17B model on all major coding benchmarks.
View source- benchmark result:
- Surpassed previous 397B MoE model
Relationships
9Deploys
Competes With
Uses
Recent Articles
2Qwen 3.6 27B Hits 34 tok/s on M5 Max MacBook Pro
+Qwen 3.6 27B hits 34 tok/s on M5 Max MacBook Pro with 90% acceptance rate, per @rohanpaul_ai. Shows viable local LLM inference on Apple Silicon.
75 relevanceHermes Agent Hits 140K GitHub Stars, Nvidia RTX as Local Inference Bedrock
+Hermes Agent hit 140K GitHub stars, most-used on OpenRouter. Runs locally on Nvidia RTX with self-evolving skills and Qwen 3.6 models that beat prior
100 relevance
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.
Sentiment History
| Week | Avg Sentiment | Mentions |
|---|---|---|
| 2026-W17 | 0.70 | 1 |
| 2026-W20 | 0.70 | 2 |