Mostly uncensored models for low VRAM budget
Naphula
Naphula
AI & ML interests
Building new model tools, merges (7B-70B), merge methods, ablations, finetunes, and datasets.
Recent Activity
updated a model about 6 hours ago
Naphula/Azure_Dusk-v0.2-MPOA updated a model about 6 hours ago
Naphula/Pygmalion-3-12B-MPOA updated a collection about 6 hours ago
Favorite Merge MethodsOrganizations
spaces 5
Running
7
Model Tools
📚
Merge and audit large language models on low‑VRAM GPUs
Running
LLM Brain Map Explorer
🏢
Create a simple static web page with editable HTML
Running
TAS 1.5
🚀
Analyze text files with advanced metrics
Running
4
GGUF Repo Suite
🦙
Create and quantize Hugging Face models
Running
Portable Offline Markdown Viewer
🌍
Portable Offline Markdown Viewer
models 162
Naphula/Azure_Dusk-v0.2-MPOA
12B • Updated
Naphula/Pygmalion-3-12B-MPOA
12B • Updated
Naphula/MN-VelvetCafe-RP-12B-V2-MPOA
Updated
Naphula/G4-Runic-Oarfish-26B-A4B-v1.1
Image-Text-to-Text • 25B • Updated • 116
Naphula/G4-Runic-Oarfish-26B-A4B-v1.2
Image-Text-to-Text • 25B • Updated • 236 • 11
Naphula/G4-Runic-Oarfish-26B-A4B-v1
Image-Text-to-Text • 25B • Updated • 173 • 4
Naphula/Salamander-24B-v1
Text Generation • 24B • Updated • 73 • 6
Naphula/Goetia-24B-v1.2
Text Generation • 24B • Updated • 37 • 16
Naphula/Goetia-24B-v1.1
Text Generation • 24B • Updated • 16 • 14
Naphula/Geodesic-Phantom-12B-GGUF
12B • Updated • 267 • 1