GGUF models by liodon-ai
122 GGUF models quantized by liodon-ai on Hugging Face. Sizes run from 94M to 34.7B parameters. The longest trained context is 1024K tokens.
GE
gemma 4 12B it imatrix
Gemma · liodon-ai
Params11.9B
Context256K
Q4_K_M7.4 GB
QW
Qwen2.5 Coder 7B Instruct imatrix
Qwen · liodon-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
DE
LoCo 7B imatrix
DeepSeek · liodon-ai
Params7.62B
Context128K
Q4_K_M4.7 GB
MI
Zephyr 7b Beta
Mistral · liodon-ai
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
HybridAgent 14B Agentic imatrix
Qwen · liodon-ai
Params14.8B
Context32K
Q4_K_M9.0 GB
LL
Llama 3 8b
Llama · liodon-ai
Params8.03B
Context8K
Q4_K_M4.9 GB
QW
Qwen2.5 Coder 1.5B Instruct imatrix
Qwen · liodon-ai
Params1.54B
Context32K
Q4_K_M1.0 GB
MI
Sentiment Analysis 7B imatrix
Mistral · liodon-ai
Params7.24B
Context32K
Q4_K_M4.4 GB
QW
Qwen2.5 7B imatrix
Qwen · liodon-ai
Params7.62B
Context128K
Q4_K_M4.7 GB
MI
MiniCPM5 1B Claude Opus Fable5 V2 Thinking imatrix
MiniCPM · liodon-ai
Params1.08B
Context128K
Q4_K_M0.7 GB
QW
Qwen3 1.7B Base imatrix
Qwen · liodon-ai
Params1.72B
Context32K
Q4_K_M1.1 GB
QW
Qwen2.5 Coder 7B imatrix
Qwen · liodon-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
LL
Llama 3.2 1B Instruct imatrix
Llama · liodon-ai
Params1.24B
Context128K
Q4_K_M0.8 GB
QW
Qwen3 4B Instruct 2507 imatrix
Qwen · liodon-ai
Params4.02B
Context256K
Q4_K_M2.5 GB
ZE
zeta 2.1 imatrix
Zeta · liodon-ai
Params8.25B
Context32K
Q4_K_M5.1 GB
QW
FastContext 1.0 4B SFT imatrix
Qwen · liodon-ai
Params4.02B
Context256K
Q4_K_M2.5 GB
LF
LFM2.5 8B A1B imatrix
Lfm · liodon-ai
Params8.47B
Context125K
Q4_K_M5.2 GB
LL
Hermes 3 Llama 3.1 8B
Llama · liodon-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
Qwen2.5 3B imatrix
Qwen · liodon-ai
Params3.09B
Context32K
Q4_K_M1.9 GB
LL
LLMBG Llama 3.1 8B BG Reasoning v0.1 imatrix
Llama · liodon-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
QW
zero imatrix
Qwen · liodon-ai
Params8.19B
Context32K
Q4_K_M5.0 GB
QW
Qwen3 14B imatrix
Qwen · liodon-ai
Params14.8B
Context40K
Q4_K_M9.0 GB
LL
CodeLlama 7b Hf
Llama · liodon-ai
Params6.74B
Context16K
Q4_K_M4.1 GB
VI
vicuna 13b self consistency random var 5 imatrix
Vicuna · liodon-ai
Params13B
Context4K
Q4_K_M7.9 GB
MY
mythos 9b unhinged imatrix
Mythos · liodon-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
QW
Qwen3 8B Base imatrix
Qwen · liodon-ai
Params8.19B
Context32K
Q4_K_M5.0 GB
QW
Qwen1.5 MoE A2.7B imatrix
Qwen · liodon-ai
Params14.3B
Context8K
Q4_K_M9.5 GB
QW
s1 mini imatrix
Qwen · liodon-ai
Params752M
Context40K
Q4_K_M0.5 GB
QW
Qwen2.5 3B Instruct imatrix
Qwen · liodon-ai
Params3.09B
Context32K
Q4_K_M1.9 GB
PH
Phi 4 Mini Instruct
Phi · liodon-ai
Params3.84B
Context128K
Q4_K_M2.5 GB