GGUF models by eaddario

43 GGUF models quantized by eaddario on Hugging Face. Sizes run from 1.08B to 37.4B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
Dolphin Mistral 24B Venice Edition
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M13.1 GB
GGUF
MI
Dolphin3.0 Mistral 24B
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M13.1 GB
GGUF
MI
Dolphin3.0 R1 Mistral 24B
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M13.1 GB
Reasoning
SP
Spark X2.5 4B
Spark · eaddario
Params4.11B
Context—
Smallest0.0 GB
GGUF
WA
Watt Tool 8B GGUF
Watt · eaddario
Params8B
Context128K
Q4_K_M4.4 GB
Tool use
QW
Qwen3.6 35B A3B
Qwen · eaddario
Params34.7B
Context—
Smallest0.4 GB
GGUF
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · eaddario
Params7.62B
Context128K
Q4_K_M4.2 GB
Reasoning
QW
Qwen3.8 27B
Qwen · eaddario
Params27.3B
Context—
Smallest0.0 GB
GGUF
HA
Hammer2.1 7b GGUF
Hammer · eaddario
Params7.61B
Context32K
Q4_K_M4.2 GB
Tool use
LL
Llama Guard 3 8B
Llama · eaddario
Params8.03B
Context128K
Q4_K_M4.4 GB
GGUF
MI
MiniCPM5 2B
MiniCPM · eaddario
Params2.52B
Context—
Smallest0.0 GB
GGUF
SP
Spark X2.5 1.7B
Spark · eaddario
Params1.71B
Context—
Smallest0.0 GB
GGUF
GE
Gemma 3 12b It
Gemma · eaddario
Params11.8B
Context128K
Q4_K_M6.4 GB
GGUF
MI
Devstral Small 2505
Mistral · eaddario
Params23.6B
Context128K
Q4_K_M12.5 GB
GGUF
MI
MiniCPM5 1B
MiniCPM · eaddario
Params1.08B
Context128K
Smallest0.0 GB
GGUF
MI
Mistral Small 3.2 24B Instruct 2506
Mistral · eaddario
Params23.6B
Context128K
Q4_K_M13.1 GB
GGUF
MI
Ministral 3 14B Instruct 2512
Mistral · eaddario
Params13.5B
Context256K
Q4_K_M8.2 GB
Tool use
GE
gemma 4 E4B it
Gemma · eaddario
Params7.52B
Context128K
Smallest0.0 GB
GGUF
MI
Mistral Small 3.2 24B Instruct 2506
Mistral · eaddario
Params22.5B
Context128K
Q4_K_M12.5 GB
GGUF
GE
gemma 4 26B A4B it
Gemma · eaddario
Params25.2B
Context256K
Smallest0.1 GB
GGUF
QW
Qwen3 30B A3B
Qwen · eaddario
Params30.5B
Context40K
Q4_K_M17.1 GB
ReasoningTool use
QW
Qwen3.5 9B
Qwen · eaddario
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
HO
K2 Horizon MoVA 36B A4B
Horizon · eaddario
Params37.4B
Context512K
Smallest0.3 GB
GGUF
QW
Qwen3 8B
Qwen · eaddario
Params8.19B
Context40K
Q4_K_M4.5 GB
ReasoningTool use
NE
IQ2 NL IQ3 NL Test Models
Nemotron · eaddario
Params8.89B
Context1024K
Smallest0.0 GB
GGUF
GE
gemma 4 E2B it
Gemma · eaddario
Params4.65B
Context128K
Smallest0.0 GB
GGUF
QW
Qwen3.5 4B
Qwen · eaddario
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
MI
Dolphin Mistral 24B Venice Edition
Mistral · eaddario
Params23.6B
Context32K
Q4_K_M12.4 GB
GGUF
GL
GLM 4.6V Flash
GLM · eaddario
Params9.4B
Context128K
Q4_K_M6.2 GB
ReasoningTool useVision
HO
K2 Horizon 7B
Horizon · eaddario
Params9B
Context512K
Smallest0.0 GB
GGUF

About eaddario on Hugging Face

eaddario has published 43 GGUF models that ggufmodels.com tracks, across families such as Mistral, Qwen and Gemma. The most downloaded are Dolphin Mistral 24B Venice Edition, Dolphin3.0 Mistral 24B and Dolphin3.0 R1 Mistral 24B.

The quants eaddario publishes most often are Q8_0 (43), Q6_K (43), F16 (43) and Q4_K_M (28). Their Q4_K_M files range from 2.7 to 17.1 GB. Parameter counts run from 1.08B to 37.4B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has eaddario published?

43 models are listed here, mainly from the Mistral, Qwen and Gemma families. The most downloaded is Dolphin Mistral 24B Venice Edition.

Which quants does eaddario publish?

The most common are Q8_0 (43 models), Q6_K (43 models), F16 (43 models) and Q4_K_M (28 models).

Keep browsing