eriktonon/ llama3.2-moe-uncensored

60 11 hours ago

Meta Llama 3.2 8x4B MoE 21B Dark-Champion Uncensored Abliterated (Q4_K_M, 12.85GB, fits in 16GB VRAM). 259.2 tok/s Decode, 15065 tok/s Prefill, 28.6% Precision, 0.0% Hallucination (6/6), 100% Zero-Refusal. License: Llama 3.2 Community.

21b

2 models

llama3.2-moe-uncensored:latest
a979dd38c799 • 13GB • 128K context window •
Text input • 11 hours ago
llama3.2-moe-uncensored:21b latest
a979dd38c799 • 13GB • 128K context window •
Text input • 11 hours ago