LLMfan46 PRO
llmfan46
AI & ML interests
If you find my work useful, consider supporting me on: https://patreon.com/LLMfan46 (vote on models, request specific abliterations) and: https://ko-fi.com/llmfan46 (one-time tips).
Recent Activity
new activity about 14 hours ago
llmfan46/Qwen3.6-27B-uncensored-heretic-v2:KL questions updated a model 1 day ago
llmfan46/Nex-N2-mini-ultra-uncensored-heretic-GGUFOrganizations
None yet
KL questions
1
#6 opened about 15 hours ago
by 
heterodoxin
New Heretic ?
5
#3 opened 3 days ago
by 
Markobes
Refusal is 10/100
2
#1 opened 5 days ago
by llmfan46
v2 when?
3
#1 opened 5 days ago
by 
yyouretoast
New activity in llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic 4 days ago
Why does ai keep switch measurement systems?
3
#1 opened 5 days ago
by 
tadams597
Will you release a abliterated or uncensored variant also?
đđ 5
6
#28 opened 10 days ago
by 
ridham034
5-bit MiniMax M3 running locally on a single M3 Ultra 512GB via Unsloth!
đđ„ 3
6
#3 opened 14 days ago
by 
danielhanchen
Create README.md
3
#1 opened about 1 month ago
by 
yangshuai-shuijiao
Can MiniMax-M3 run on 2x NVIDIA DGX Spark 4TB?
5
#16 opened 9 days ago
by 
abosk
nvfp4
1
#1 opened 7 days ago
by 
jeffbenson1979
GLM5.2 pls!!!!
đ 1
3
#1 opened 10 days ago
by 
Pragmatism0220
metadata errors while quantizing
1
#1 opened 9 days ago
by 
trgtszr
Is vision/multimodal input supported in this GGUF build?
3
#8 opened 10 days ago
by 
grubwithu
Comparison with M2.7 with same file size? What dou you think?
đ 2
3
#6 opened 13 days ago
by 
hendrik289
Anyone get this working on 2x rtx 6000 pro?
đ„ 5
1
#10 opened 13 days ago
by 
Quadrapole
MTP assistant?
1
#4 opened 11 days ago
by Markobes
Does not load into vllm- layer 5 fusion issue
2
#1 opened 12 days ago
by 
mancub
Is MTP supported?
3
#5 opened 14 days ago
by 
SlavikF
Is the mmproj different from the original?
1
#2 opened 13 days ago
by 
SirVeggie