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.
Organizations
None yet
What inference engine/runtime is needed for this to be run?
👍 2
3
#2 opened 2 months ago
by Smoffyy
Request for pure quantized Gemma4 E2B version
2
#1 opened 4 months ago
by 
okasi
Fully Open-Sourced, or just Open-Weight?
2
#2 opened 6 months ago
by Smoffyy
Upload qwen3_nonthinking.jinja
#2 opened 6 months ago
by Smoffyy
Update README.md
#1 opened 6 months ago
by Smoffyy
Update README.md
#2 opened 6 months ago
by Smoffyy
Upload the nonthinking chattemplate
#1 opened 6 months ago
by Smoffyy
Upload mmproj and chat templateee
#2 opened 6 months ago
by Smoffyy
Upload readme
#1 opened 6 months ago
by Smoffyy
Upload q4_k_m, q5_k_m and q8_0 ggufssss
#3 opened 7 months ago
by Smoffyy
Update README.md
#2 opened 7 months ago
by Smoffyy
Upload q8_0, q4_k_m and q5_k_m and licenseee
#1 opened 7 months ago
by Smoffyy
Reupload F16, q8_0, q4_k_m, q5_k_m, pure gguf's with proper licensing.
#4 opened 7 months ago
by Smoffyy
Upload q4_k_m, q5_k_m and q8_0.
#2 opened 7 months ago
by Smoffyy
Upload F16, and mmproj.
#1 opened 7 months ago
by Smoffyy
upload other formats.
#3 opened 7 months ago
by Smoffyy
gpt-oss-20b?
2
#5 opened 9 months ago
by Smoffyy
gpt-oss-20b?
2
#5 opened 9 months ago
by Smoffyy