LLMfan46
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 12 hours ago
llmfan46/Qwen3.5-9B-ultra-heretic:ARA technique new activity about 21 hours ago
llmfan46/Qwen3.5-27B-heretic-v2-GGUF:Question on layer wise quantization scheme updated a model 1 day ago
llmfan46/Qwen3.5-9B-ultra-heretic-GGUFOrganizations
None yet
ARA technique
29
#1 opened 4 days ago
by 
AusCon
Question on layer wise quantization scheme
8
#2 opened 5 days ago
by 
sunnyyy
Jinja Template
25
#1 opened 3 days ago
by 
SerialKicked
I will be testing fewer finetunes/merges
β€οΈπ 18
11
#624 opened 6 days ago
by 
DontPlanToEnd
Can you make a heretic version of Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled?
π 1
12
#4 opened 22 days ago
by 
xldistance
Impressive work!
π 1
1
#1 opened 5 days ago
by 
tarruda
IQ4_KSS?
3
#1 opened 6 days ago
by 
Austriani
Eval Request: Q3.5-BlueStar-v2-27B
π₯ 1
1
#625 opened 6 days ago
by llmfan46
Eval Request: MS3.2-PaintedFantasy-v4.1-24B
#622 opened 6 days ago
by llmfan46
Settings
2
#2 opened 7 days ago
by 
jeffbenson1979
Eval Request: Qwen3.5-35B-A3B
β 1
#621 opened 7 days ago
by llmfan46
Eval Request: llmfan46/gemma-3-27b-it-ultra-uncensored-heretic
1
#620 opened 8 days ago
by 
Darkknight535
Eval Request: Omega-Darker-Gaslight_The-Final-Forgotten-Fever-Dream-24B
#618 opened 9 days ago
by llmfan46
eval request
π 1
2
#613 opened 9 days ago
by 
drmcbride
Eval request: llmfan46/gpt-oss-120b-heretic-v2
π 2
1
#588 opened 21 days ago
by llmfan46
Eval Request: gpt-oss-120b
π 1
1
#611 opened 10 days ago
by llmfan46
ARA version for 9B/27B/35B-A3B?
6
#7 opened 19 days ago
by 
Iwaku-Real
Better or worse than v2?
4
#1 opened 17 days ago
by AusCon
Eval Request: llmfan46/Mistral-Small-3.2-24B-Instruct-2506-ultra-uncensored-heretic
#610 opened 10 days ago
by llmfan46