Lockout
Lockout
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
bertbobson/FLUX.2-klein-9B-INT8-Comfy:What was the process to quantize?
new activity
17 days ago
QuixiAI/Ina-v11.1:Its actually good model.
new activity
17 days ago
BruhzWater/Sapphira-L3.3-70b-0.1:The best model in the world for 5 months already
Organizations
None yet
What was the process to quantize?
1
#1 opened 1 day ago
by
Lockout
Its actually good model.
#1 opened 17 days ago
by
Lockout
The best model in the world for 5 months already
🔥
1
1
#4 opened about 2 months ago
by
deleted
Optimized Quant between 3bpw and 3.5bpw
32
#1 opened about 1 month ago
by
remichu
Eval: https://huggingface.co/QuixiAI/Ina-v11.1 70b
#494 opened 29 days ago
by
Lockout
Anyone found any obvious differences compared to using the stock model?
8
#4 opened about 2 months ago
by
mingyi456
EVAL: Behemoth-X V2.1
#459 opened about 2 months ago
by
Lockout
What's up with this version?
#1 opened about 2 months ago
by
Lockout
Please Upload the Safetensors
👍
1
4
#1 opened about 2 months ago
by
PlayAI
This model seems truly unusable for RP.
1
#3 opened 3 months ago
by
Lockout
Why does it ramble?
#15 opened 3 months ago
by
Lockout
Model updates
❤️
2
2
#1 opened 3 months ago
by
Lockout
These don't really work.
5
#1 opened 3 months ago
by
Lockout
I think the dataset is gonna have to be more diverse.
🤯
1
#1 opened 3 months ago
by
Lockout
Definitely does NOT run on dual RTX PRO 6000 96GB
👍
1
3
#2 opened 3 months ago
by
aaron-newsome
2.97 or 3.0 quant?
1
#1 opened 3 months ago
by
Lockout
Actually slower than Q4K and Q3K quants
3
#1 opened 3 months ago
by
Lockout
2.25 bpw perplexity
20
#2 opened 4 months ago
by
malamen4
Multiple chat template fixes
🚀
❤️
7
14
#2 opened 4 months ago
by
danielhanchen