The compression ladder, recipes, adapters and unrepaired variants behind the family.
David
logic65
AI & ML interests
AI tinkerer in South Africa. I take language models apart on two 8GB gaming GPUs to see what's inside, then put smaller ones back together. Everything I break and everything I learn ships public. Support the tinkering: ko-fi.com/davida81328
Recent Activity
updated a model about 19 hours ago
logic65/whittle-dev updated a model 2 days ago
logic65/Whittle-Next-27B-A3B updated a model 2 days ago
logic65/Whittle-Qwen-3.8-35B-A3B-GGUFOrganizations
None yet
models 23
logic65/whittle-dev
36B • Updated • 19 • 1
logic65/Whittle-Qwen-3.8-35B-A3B-GGUF
Text Generation • 36B • Updated • 436 • 2
logic65/Whittle-Qwen-3.8-35B-A3B
Text Generation • 36B • Updated • 919 • 3
logic65/Whittle-Next-27B-A3B
Text Generation • 28B • Updated • 4.55k • 20
logic65/Whittle-Next-27B-A3B-GGUF
Text Generation • 28B • Updated • 2.88k • 8
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF
Text Generation • 27B • Updated • 56.7k • 28
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B
27B • Updated • 39.2k • 117
logic65/Whittle-Next-26B-A3B
Text Generation • 27B • Updated • 175 • 1
logic65/Qwen3.8-Whittle-tri-14.7B-chat
15B • Updated • 7.61k • 3
logic65/Qwen3.6-Whittle-25B-A3B
Text Generation • 25B • Updated • 1.04k • 1