AIHacker Noonabout 4 hours ago
Inside Qwen3.6 Genesis Hermes V9
12 min read
LuffyTheFox created Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V9-GGUF, a 35-billion parameter mixture-of-experts language model. The Genesis tensor repair technique reduces training noise. It runs 3 billion active parameters through 256 experts, with 262,000 native context tokens.
Level
Hype check
Tap to vote and see what everyone thinks.
