Qwen 3.7
Backend wars, Mac math, and the back-catalog refresh
Three speculative-decoding backends benched head to head on a single RTX 3090. The VRAM calculator finally caught up. And a 120-article audit found stale Qwen 2.5 recommendations.
Qwen 3.7 Preview Scored 57 AAI: 27B/35B Open Weights Next
Qwen 3.7 Max scored 57 on Artificial Analysis (+5 over 3.6 Max), #1 of 218 ranked. Open 27B/35B weights coming. InsiderLLM benches within 24h of drop.