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.

Most downloadedNewestLargestLongest contextSmallest
DE
DeepHat V1 7B imatrix
Deephat · liodon-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen3.6 35B A3B imatrix
Qwen · liodon-ai
Params34.7B
Context256K
Q4_K_M21.2 GB
GGUF
DE
DeepSeek R1 Distill Qwen 14B imatrix
DeepSeek · liodon-ai
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
QW
Octen WebGR 0.6B imatrix
Qwen · liodon-ai
Params730M
Context32K
Q4_K_M0.5 GB
ReasoningTool use
QW
novel humanize 4b imatrix
Qwen · liodon-ai
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
MI
Riva Translate 4B Instruct v2 imatrix
Mistral · liodon-ai
Params4.2B
Context8K
Q4_K_M2.8 GB
GGUF
QW
Octen WebGR 4B imatrix
Qwen · liodon-ai
Params4.36B
Context32K
Q4_K_M2.8 GB
ReasoningTool use
QW
Qwen2.5 Coder 14B Instruct imatrix
Qwen · liodon-ai
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
AL
ALoDLM 8B imatrix
Alodlm · liodon-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
LL
Llama 3.2 3B Instruct imatrix
Llama · liodon-ai
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
novel humanize 4b
Qwen · liodon-ai
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
AL
ALoDLM 8B
Alodlm · liodon-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen 3 8b Heretic
Qwen · liodon-ai
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
LO
LocateAnything 3B imatrix
Locateanything · liodon-ai
Params3.4B
Context32K
Q4_K_M2.1 GB
Tool useVision
QW
Carbon X imatrix
Qwen · liodon-ai
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen3 14B Base imatrix
Qwen · liodon-ai
Params14.8B
Context32K
Q4_K_M9.0 GB
ReasoningTool use
SU
Supra2 100M Instruct imatrix
Supra · liodon-ai
Params101M
Context2K
Q4_K_M0.1 GB
GGUF
MA
MaralGPT Mythos 9B 2606
Maralgpt · liodon-ai
Params8.95B
Context1024K
Q4_K_M5.6 GB
ReasoningTool use
CO
colgrep agent 2B imatrix
Colgrep · liodon-ai
Params2.52B
Context128K
Q4_K_M1.6 GB
ReasoningTool use
QW
VulnLLM R 7B imatrix
Qwen · liodon-ai
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
dwight 4b imatrix
Qwen · liodon-ai
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool use
DE
DeepSeek R1 Distill Qwen 1.5B imatrix
DeepSeek · liodon-ai
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
MI
zephyr 7b alpha imatrix
Mistral · liodon-ai
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
UserLM 2.0
Llama · liodon-ai
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
gemma 4 12B it
Gemma · liodon-ai
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool use
OR
Ornith 1.0 35B
Ornith · liodon-ai
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
MI
Vikhr Nemo 12B Instruct R 21 09 24 imatrix
Mistral · liodon-ai
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
DE
LoCo 7B
DeepSeek · liodon-ai
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
QW
Qwable 3.6 27b imatrix
Qwable · liodon-ai
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
SQ
sqlcoder 7b 2 imatrix
Sqlcoder · liodon-ai
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding

About liodon-ai on Hugging Face

liodon-ai has published 122 GGUF models that ggufmodels.com tracks, across families such as Qwen, Wav and Llama. The most downloaded are DeepHat V1 7B imatrix, Qwen3.6 35B A3B imatrix and DeepSeek R1 Distill Qwen 14B imatrix.

The quants liodon-ai publishes most often are Q8_0 (122), Q6_K (107), Q5_K_M (107) and Q4_K_M (107). Their Q4_K_M files range from 0.1 to 21.2 GB. Parameter counts run from 94M to 34.7B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has liodon-ai published?

122 models are listed here, mainly from the Qwen, Wav and Llama families. The most downloaded is DeepHat V1 7B imatrix.

Which quants does liodon-ai publish?

The most common are Q8_0 (122 models), Q6_K (107 models), Q5_K_M (107 models) and Q4_K_M (107 models).

Keep browsing