scima/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF-all-quants Text Generation • 27B • Updated Aug 24 • 1.05k • 5
scima/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF-all-quants Text Generation • 27B • Updated Aug 24 • 1.05k • 5
Whittle: research and dev Collection The compression ladder, recipes, adapters and unrepaired variants behind the family. • 2 items • Updated 24 days ago • 2
Whittle: models you can run Collection Compressed Qwen3.8-27B variants with weights published and tested. Start here. • 4 items • Updated 24 days 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. • 1 item • Updated 24 days ago • 1
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF Image-Text-to-Text • 9B • Updated 19 days ago • 2.03M • 1.42k