GigaToken: ~1000x faster Language model tokenization 4 hours agowow, best release all week. 0ThreadHN
Qwen 3.6 27B is the sweet spot for local development 23 days agoYup, been rocking theQwen3.6-35B-A3B-MTP-GGUF locally with 88tk/s it's amazing. 0ThreadHN