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.
SM
SmolLM2 1.7 Persona Q5 K M
SmolLM · bunnycore
Params1.71B
Context8K
Smallest1.2 GB
LL
Llama 3.2 3B
Llama · bunnycore
Params3.21B
Context128K
Q4_K_M2.0 GB
GR
Huihui Granite 4.0 H Micro Abliterated
Granite · bunnycore
Params3.19B
Context1024K
Smallest2.3 GB
QW
QwenMosaic 7B Q5 K M
Qwen · bunnycore
Params7.62B
Context32K
Smallest5.4 GB
LL
Best Mix Llama 3.1 8B IQ4 NL
Llama · bunnycore
Params8.03B
Context128K
Smallest4.7 GB
LL
Llama 3.2 1B General Best Q5 K M
Llama · bunnycore
Params1.24B
Context128K
Smallest0.9 GB
BE
BestofLLama3 8B stock Q5 K M
Bestofllama · bunnycore
Params8.03B
Context8K
Smallest5.7 GB
PH
Phi 4 RP
Phi · bunnycore
Params14.7B
Context16K
Q4_K_M8.9 GB
QW
Qwen3 4B Goat
Qwen · bunnycore
Params4.02B
Context40K
Smallest3.3 GB
PH
Phi 3.5 Mini Hyper Q4 K M
Phi · bunnycore
Params3.82B
Context128K
Q4_K_M2.4 GB
QW
Qwen3 1.7B FreeSteer
Qwen · bunnycore
Params1.72B
Context40K
Smallest1.8 GB
QW
CyberCore Qwen 2.1 7B Q5 K M
Qwen · bunnycore
Params7.62B
Context128K
Smallest5.4 GB
PH
Phi 3.5 mini TitanFusion 0.4.1 Q4 K M
Phi · bunnycore
Params3.82B
Context128K
Q4_K_M2.4 GB
CH
Chimera Apex 7B Q5 K M
Chimera · bunnycore
Params7.24B
Context32K
Smallest5.1 GB
QW
Qwen3 1.7B Nyx Fusion
Qwen · bunnycore
Params2.03B
Context40K
Smallest2.2 GB
FU
FuseQwQen 7B Q5 K M
Fuseqwqen · bunnycore
Params7.62B
Context32K
Smallest5.4 GB
QW
Qwen2.5 7B HyperMix IQ4 NL
Qwen · bunnycore
Params7.62B
Context32K
Smallest4.4 GB
QW
Qwen2.5 3B RP Thinker V2 Q6 K
Qwen · bunnycore
Params3.4B
Context32K
Smallest2.8 GB
LL
Llama 3.2 3B TitanFusion IQ4 NL
Llama · bunnycore
Params3.61B
Context128K
Smallest2.1 GB
QW
Qwen 2.5 3b Evol CoT IQ4 NL
Qwen · bunnycore
Params3.4B
Context32K
Smallest2.0 GB
QA
QandoraExp 7B
Qandoraexp · bunnycore
Params7.62B
Context128K
Smallest5.4 GB
QW
Qwen2.5 7B Instruct Fusion
Qwen · bunnycore
Params7.62B
Context128K
Smallest5.4 GB
LL
Llama 3.1 8B OmniMatrix IQ4 NL
Llama · bunnycore
Params8.03B
Context128K
Smallest4.7 GB
LL
Llama 3.2 3B R1 Lora
Llama · bunnycore
Params24M
Context—
Smallest0.1 GB
GE
Gemma 2 2B Smart Q8 0
Gemma · bunnycore
Params2.61B
Context8K
Smallest2.8 GB
GE
Gemma2 9B TitanFusion
Gemma · bunnycore
Params9.24B
Context8K
Q4_K_M5.8 GB
GE
GemmaOmni2 2B Q5 K M
Gemma · bunnycore
Params2.61B
Context8K
Smallest1.9 GB
LL
Llama 3.2 3B CodeReactor IQ4 NL
Llama · bunnycore
Params3.21B
Context128K
Smallest1.9 GB
GO
GoldenLlama 3.1 8B Q4 K M
Goldenllama · bunnycore
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen2.5 3B RP Thinker Q5 K M
Qwen · bunnycore
Params3.4B
Context32K
Smallest2.4 GB