GGUF models by llmfan46

97 GGUF models quantized by llmfan46 on Hugging Face. Sizes run from 447M to 426B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
OM
Omega Evolution 27B v2.0 Ultra Uncensored Heretic
Omega · llmfan46
Params26.9B
Context256K
Q4_K_M16.2 GB
ReasoningRoleplayTool use
FO
Forgotten Abomination 36B v4.1 Uncensored Heretic
Forgotten · llmfan46
Params36.9B
Context32K
Q4_K_M22.4 GB
Roleplay
FO
Forgotten Transgression 24B v4.1 Uncensored Heretic
Forgotten · llmfan46
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
MI
MiniMax M3 uncensored heretic aggressive compressed quants pack
Minimax · llmfan46
Params426B
Context1024K
Q4_K_M258.0 GB
ReasoningTool useVision
OM
Omega Evolution 27B v2.0 Uncensored Heretic
Omega · llmfan46
Params26.9B
Context256K
Q4_K_M16.2 GB
ReasoningRoleplayTool use
OM
Omega Evolution 27B v2.1 Uncensored Heretic
Omega · llmfan46
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplayTool use
MI
MiniMax M3 uncensored heretic aggressive high precision pack
Minimax · llmfan46
Params426B
Context1024K
Smallest350.5 GB
ReasoningTool useVision

Keep browsing