logic65/whittle-next
16B • Updated • 206 • 2
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
new activity about 1 hour ago
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF:slow than 27b-gguf-q4 updated a model 1 day ago
logic65/Qwen3.8-Whittle-Next-19.8B-A11B-chat published a model 1 day ago
logic65/Qwen3.8-Whittle-Next-19.8B-A11B-chatOrganizations
None yet
logic65/Qwen3.8-Whittle-Next-19.8B-A11B-chat
20B • Updated
logic65/Qwen3.8-Whittle-Next-19.8B-A10B-base
Text Generation • 20B • Updated • 899 • 1
logic65/whittle-next-moe-test
Text Generation • 15B • Updated • 1.36k
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B
27B • Updated • 27.7k • 109
logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF
Text Generation • 27B • Updated • 40k • 21
logic65/Qwen3.8-Whittle-dev
Updated • 1
logic65/Qwen3.8-Whittle-tri-14.7B-chat
15B • Updated • 4.49k • 3
logic65/Qwen3.8-p44w75-16.8B-unrepaired
Text Generation • 16B • Updated • 7.46k • 2
logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired
Text Generation • 18B • Updated • 1.14k • 1
logic65/Qwen3.8-Whittle-tri-kd-lora
Updated • 27 • 1
logic65/Qwen3.8-Whittle-tri-14.7B
Text Generation • 15B • Updated • 2.79k • 1
logic65/Qwen3.8-Whittle-16B
Text Generation • 16B • Updated • 6.12k • 2
logic65/Qwen3.8-Whittle-v40-16.8B
Text Generation • 18B • Updated • 414 • 1
logic65/Qwen3.8-Whittle-48L-cut
Text Generation • Updated • 1
logic65/Qwen3.8-Whittle-44L-cut
Text Generation • Updated • 1
logic65/about
Updated • 1