mav23/Hermes-3-Llama-3.1-70B-lorablated-GGUF
Updated
•
126
•
1
Erin M
Pragmatica
·
AI & ML interests
Uncensored, neutrally aligned, user aligned 8-bit MLX models under 100 billion parameters. Run models locally on an M4 Max MacBook Pro with 128GB of RAM. Roleplay tuned models and uncensored AI companions.
Recent Activity
liked
a model
about 20 hours ago
mav23/Hermes-3-Llama-3.1-70B-lorablated-GGUF
liked
a model
about 21 hours ago
mlx-community/Hermes-3-Llama-3.1-70B-8bit
liked
a model
about 21 hours ago
cognitivecomputations/Dolphin3.0-R1-Mistral-24B
Organizations
None yet
Pragmatica's activity
liked
a
model
about 20 hours ago
liked
4
models
about 21 hours ago
mlx-community/Hermes-3-Llama-3.1-70B-8bit
Updated
•
5
•
3
cognitivecomputations/Dolphin3.0-R1-Mistral-24B
Text Generation
•
Updated
•
4.09k
•
143
DavidAU/DeepSeek-MOE-4X8B-R1-Distill-Llama-3.1-Mad-Scientist-24B-GGUF
Text Generation
•
Updated
•
1.2k
•
3
mlx-community/r1-1776-distill-llama-70b-8bit
Updated
•
74
•
3