GGUF models by bunnycore
161 GGUF models quantized by bunnycore on Hugging Face. Sizes run from 1M to 14.7B parameters. The longest trained context is 1024K tokens.
PH
Phi 3.5 mini TitanFusion 0.3 IQ4 XS
Phi · bunnycore
Params3.82B
Context128K
Smallest2.1 GB
MI
Microtron 4B Q4 K M
Microtron · bunnycore
Params4.51B
Context128K
Q4_K_M2.8 GB
MO
Mobitron 4B Q5 K M
Mobitron · bunnycore
Params4.51B
Context128K
Smallest3.2 GB
LL
LLama3-Mix-8B
Llama · bunnycore
Params8.03B
Context8K
Q4_K_M4.9 GB
IN
L3 Intermix v0.2 Q4 K M
Intermix · bunnycore
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen2.5 3B Model Stock
Qwen · bunnycore
Params3.4B
Context32K
Smallest2.4 GB
LL
Blackbird-Llama-3-8B
Llama · bunnycore
Params8.03B
Context8K
Smallest5.7 GB
LL
Llama3-OneForAll-8B
Llama · bunnycore
Params8.03B
Context8K
Q4_K_M4.9 GB
IN
L3 8B Intermix v0.3 Q5 K M
Intermix · bunnycore
Params8.03B
Context8K
Smallest5.7 GB
FU
FunLLama3-8B
Funllama · bunnycore
Params8.03B
Context8K
Smallest5.7 GB
LL
Llama 3 Intermix Q5 K M
Llama · bunnycore
Params8.03B
Context8K
Smallest5.7 GB