GGUF models by AtomicChat

102 GGUF models quantized by AtomicChat on Hugging Face. Sizes run from 2M to 2780B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
TE
Ternary Bonsai 2 2B Uncensored LoRA
Ternary · AtomicChat
Params2B
Context—
Smallest0.0 GB
GGUF
HY
Hy3
AtomicChat
Params299B
Context256K
Q4_K_M184.7 GB
ReasoningTool use
IM
P H3 Image
Image · AtomicChat
Params20.2B
Context—
Smallest9.0 GB
GGUF
TE
Ternary Bonsai 2 4B Uncensored LoRA
Ternary · AtomicChat
Params4B
Context—
Smallest0.0 GB
GGUF
LI
Ling-3.1-flash-1019
Ling · AtomicChat
Params572B
Context256K
Smallest226.8 GB
ReasoningTool use
OR
Ornith 35B
Ornith · AtomicChat
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Atomic Chat / Qwen3-Coder 30B-A3B DFlash
Qwen · AtomicChat
Params474M
Context256K
Smallest0.5 GB
CodingTool use
QW
Atomic Chat / Qwen3-Coder Next DFlash
Qwen · AtomicChat
Params474M
Context256K
Smallest0.5 GB
CodingTool use
QW
Atomic Chat / Qwen3.6 27B DFlash
Qwen · AtomicChat
Params1.73B
Context256K
Smallest1.8 GB
ReasoningTool use
QW
Atomic Chat / Qwen AgentWorld 35B A3B
Qwen · AtomicChat
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
QW
Atomic Chat / Qwen3 8B DFlash
Qwen · AtomicChat
Params1.05B
Context40K
Smallest1.1 GB
ReasoningTool use
QW
Atomic Chat / Qwen3.5 27B DFlash
Qwen · AtomicChat
Params2.13B
Context256K
Smallest2.3 GB
ReasoningTool use
LI
Ling 3.0 Flash Fin
Ling · AtomicChat
Params127B
Context256K
Smallest108.5 GB
ReasoningTool use

Keep browsing