Latest out of the Mellum 2 family from JetBrains, Pure GGUF's.
Smoffyy
Smoffyy
AI & ML interests
I upload whatever quantizations I can, with a focus on keeping them pure. My profile also serves as a model archive, allowing anyone to download older models throughout history.
Recent Activity
published a model about 2 hours ago
Smoffyy/Mellum2-12B-A2.5B-Instruct-Thinking-Pure-GGUF updated a model about 2 hours ago
Smoffyy/Mellum2-12B-A2.5B-Instruct-Thinking-Pure-GGUF updated a model about 2 hours ago
Smoffyy/Mellum2-12B-A2.5B-Instruct-Pure-GGUFOrganizations
None yet
models 24
Smoffyy/Mellum2-12B-A2.5B-Instruct-Thinking-Pure-GGUF
Text Generation • 12B • Updated • 1
Smoffyy/Mellum2-12B-A2.5B-Instruct-Pure-GGUF
Text Generation • 12B • Updated
Smoffyy/Gemma4-31B-Instruct-Pure-GGUF
Image-Text-to-Text • 31B • Updated • 426
Smoffyy/Gemma4-E2B-Instruct-Pure-GGUF
Image-Text-to-Text • 5B • Updated • 676 • 1
Smoffyy/Qwen-Open-System-Prompts
Updated
Smoffyy/Qwen2.5-7B-1M-Instruct-Pure-GGUF
Text Generation • 8B • Updated • 593 • 2
Smoffyy/Revised-Qwen-Templates
Updated • 1
Smoffyy/Qwen3.6-35B-A3B-Instruct-Revised-GGUF
Image-Text-to-Text • 35B • Updated • 3.08k • 2
Smoffyy/Qwen3.5-27B-Instruct-Revised-GGUF
Image-Text-to-Text • 27B • Updated • 1.35k
Smoffyy/Qwen3.6-27B-Instruct-Revised-GGUF
Image-Text-to-Text • 27B • Updated • 3.13k • 3
datasets 0
None public yet