scima/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF-all-quants Text Generation • 27B • Updated 9 days ago • 2.9k • 1
scima/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF-all-quants Text Generation • 27B • Updated 9 days ago • 2.9k • 1
Whittle: research and dev Collection The compression ladder, recipes, adapters and unrepaired variants behind the family. • 9 items • Updated 11 days ago • 2
Whittle: models you can run Collection Compressed Qwen3.8-27B variants with weights published and tested. Start here. • 2 items • Updated about 3 hours ago • 2
Qwen3.8 Whittle family Collection A 27B whittled on two 8GB GPUs: measured cuts, heals, and restorations. 48L = best untrained, Whittle-16B = best overall. • 8 items • Updated 16 days ago • 1
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF Image-Text-to-Text • 9B • Updated 10 days ago • 868k • 547