GGUF models by viniciusianni

37 GGUF models quantized by viniciusianni on Hugging Face. Sizes run from 891M to 32.8B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
Mamba Codestral 7B v0.1
Mistral · viniciusianni
Params7.29B
Context1024K
Q4_K_M4.1 GB
Coding
MI
Devstral Small 2 24B Instruct 2512
Mistral · viniciusianni
Params23.6B
Context384K
Q4_K_M14.3 GB
Coding
QW
Qwen2.5 Coder 14B
Qwen · viniciusianni
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
PH
Phi 4 Mini Reasoning
Phi · viniciusianni
Params3.84B
Context128K
Smallest4.1 GB
CodingReasoningTool use
MI
Codestral 22B v0.1
Mistral · viniciusianni
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
QW
Qwen2.5 Coder 32B Instruct
Qwen · viniciusianni
Params32.8B
Context32K
Q4_K_M19.9 GB
CodingTool use
QW
Qwen3 Coder 30B A3B Instruct
Qwen · viniciusianni
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
MI
Mamba Codestral 7B v0.1
Mistral · viniciusianni
Params7.29B
Context1024K
Smallest7.8 GB
Coding
GE
Gemma 4 26B A4B It
Gemma · viniciusianni
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
PH
Phi 4 Mini Instruct
Phi · viniciusianni
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingTool use
LF
LFM2.5 1.2B Instruct
Lfm · viniciusianni
Params1.17B
Context125K
Q4_K_M0.7 GB
GGUF
GL
GLM OCR
GLM · viniciusianni
Params891M
Context128K
Smallest1.0 GB
GGUF
GR
Granite 4.1 8b
Granite · viniciusianni
Params8.79B
Context128K
Q4_K_M5.3 GB
GGUF
GE
Gemma 4 26B A4B It
Gemma · viniciusianni
Params25.2B
Context256K
Smallest26.9 GB
Vision
GR
Granite 4.1 30b
Granite · viniciusianni
Params28.9B
Context128K
Q4_K_M17.5 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · viniciusianni
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
QW
Qwen3.5 9B
Qwen · viniciusianni
Params9.2B
Context256K
Smallest9.8 GB
ReasoningTool useVision
PH
Phi 4 Mini Reasoning
Phi · viniciusianni
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingReasoningTool use
MI
Ministral 3 3B Instruct 2512
Mistral · viniciusianni
Params3.43B
Context256K
Q4_K_M2.1 GB
GGUF
GE
Gemma 3n E4B It
Gemma · viniciusianni
Params6.87B
Context32K
Q4_K_M4.8 GB
Vision
LL
Llama 3.1 8B Instruct
Llama · viniciusianni
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
GE
Gemma 4 E4B It
Gemma · viniciusianni
Params7.52B
Context128K
Q4_K_M5.3 GB
GGUF
QW
WebWorld 14B
Qwen · viniciusianni
Params14.8B
Context40K
Smallest15.7 GB
ReasoningTool use
PH
Phi 4 Mini Instruct
Phi · viniciusianni
Params3.84B
Context128K
Smallest4.1 GB
CodingTool use
GR
Granite Speech 4.1 2b
Granite · viniciusianni
Params1.84B
Context4K
Smallest2.0 GB
GGUF
GE
Gemma 3n E4B It
Gemma · viniciusianni
Params6.87B
Context32K
Smallest7.4 GB
Vision
GR
Granite 4.1 8b
Granite · viniciusianni
Params8.79B
Context128K
Smallest9.3 GB
GGUF
GE
Gemma 4 E4B It
Gemma · viniciusianni
Params7.52B
Context128K
Smallest8.0 GB
GGUF
QW
Qwen3.5 9B
Qwen · viniciusianni
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
QW
WebWorld 8B
Qwen · viniciusianni
Params8.19B
Context40K
Smallest8.7 GB
ReasoningTool use

About viniciusianni on Hugging Face

viniciusianni has published 37 GGUF models that ggufmodels.com tracks, across families such as Qwen, Mistral and Gemma. The most downloaded are Mamba Codestral 7B v0.1, Devstral Small 2 24B Instruct 2512 and Qwen2.5 Coder 14B.

The quants viniciusianni publishes most often are Q4_K_M (20) and Q8_0 (17). Their Q4_K_M files range from 0.7 to 19.9 GB. Parameter counts run from 891M to 32.8B, and the longest trained context window is 1024K tokens.

Frequently asked questions

What GGUF models has viniciusianni published?

37 models are listed here, mainly from the Qwen, Mistral and Gemma families. The most downloaded is Mamba Codestral 7B v0.1.

Which quants does viniciusianni publish?

The most common are Q4_K_M (20 models) and Q8_0 (17 models).

Keep browsing