I hate writing cuda kernels
Damien
el4
AI & ML interests
I do anything really | #quantwizard | ETH: 0xDEE7fa8C421BD038D32e4441ea1aDe72fE973706
Recent Activity
repliedto Banaxi-Tech's post 3 days ago
BananaMind is in the google situation before argon right now, right? new activity 3 days ago
InternScience/Sage-A1.5:Cheers to the best qwen 35b moe finetune ive used so far! 🍺 updated a collection 3 days ago
TOFFEEOrganizations
models 17
el4/Sage-A1.5-TOFFEE-GGUF
Text Generation • 36B • Updated • 927 • 2
el4/Ornith-1.5-9B-DFlash-GGUF
1B • Updated • 335
el4/Whittle-Qwen-3.8-35B-A3B-ONYX-GGUF
Text Generation • 36B • Updated • 1.58k • 4
el4/Ornith-1.5-35B-A3B-ONYX-GGUF
Text Generation • 36B • Updated • 492 • 4
el4/Qwen3.8-27B-ONYX-GGUF
Text Generation • 27B • Updated • 180 • 7
el4/Nemotron-3.5-Lightning-30B-A3B-ONYX-GGUF
Text Generation • 33B • Updated • 98 • 3
el4/Agents-A1-ONYX-GGUF
Text Generation • 35B • Updated • 525 • 2
el4/SIQ-1-35B-ONYX-GGUF
Text Generation • 35B • Updated • 322 • 5
el4/SIQ-1-35B-OPAL-GGUF
Text Generation • 35B • Updated • 175 • 1
el4/SIQ-1-35B-APEX-GGUF
Text Generation • 35B • Updated • 320 • 3