Coverage (30d)
2vs1
This Week
0vs0
Evidence
1 articlesRelationships
2Timeline
Qwen3.6-27B2026-05-15
Qwen 3.6 27B achieves 34 tok/s on M5 Max MacBook Pro with 90% acceptance rate
MiniMax M2.52026-05-06
Announced achievement of 400 TPS on SambaNova hardware.
Qwen3.6-27B2026-04-22
Achieved flagship-level coding performance, surpassing the larger Qwen3.5-397B-A17B model on all major coding benchmarks.
MiniMax M2.52025-03-01
MiniMax released M2 with full attention, deeming efficient attention not production-ready
Ecosystem
Qwen3.6-27B
deploysMixture of Experts (Sparse MoE for LLMs)1 src
competes withMiniMax M2.51 src
competes withClaude Code1 src
competes withQwen 3.5 397B-A17B1 src
MiniMax M2.5
competes withQwen3.6-27B1 src