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

upvoted an article about 4 hours ago

Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem

liked a model about 4 hours ago

Qwen/Qwen3.8-27B

new activity about 7 hours ago

logic65/Whittle-Next-27B-A3B-GGUF:Can it do vision?

View all activity

Organizations

None yet

New activity in logic65/Whittle-Next-27B-A3B-GGUF about 7 hours ago

Can it do vision?

#2 opened about 16 hours ago by

vac59

New activity in logic65/Whittle-Next-27B-A3B 16 days ago

how did you get it to 27b?

#2 opened 17 days ago by

Cyronius

New activity in logic65/Whittle-Next-27B-A3B 17 days ago

Great job, hope you find a sponsor

#1 opened 17 days ago by

miifanboy

New activity in huggingface/InferenceSupport 17 days ago

logic65/Whittle-Next-27B-A3B

#12344 opened 17 days ago by

logic65

New activity in logic65/Qwen3.8-Whittle-MoE-27B-A17.8B 21 days ago

Multilingual degradation observation (v2.2.1, CJK)

#4 opened 21 days ago by

underlotus

New activity in logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF 28 days ago

slow than 27b-gguf-q4

#2 opened 28 days ago by

fweifsd

New activity in logic65/Qwen3.8-Whittle-MoE-27B-A17.8B about 1 month ago

how to use this model in ollama

#2 opened about 1 month ago by

salehmgh

incorrect config.json

#3 opened about 1 month ago by

tclf90

New activity in logic65/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF about 1 month ago