GGUF models by fernandoruiz

94 GGUF models quantized by fernandoruiz on Hugging Face. Sizes run from 11M to 46.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
ER
ERNIE 4.5 21B A3B PT
Ernie · fernandoruiz
Params21.8B
Context128K
Smallest12.4 GB
GGUF
MA
madlad400 3b mt Q4 K S
Madlad · fernandoruiz
Params2.94B
Context512
Smallest1.7 GB
GGUF
GE
Gemma 3 1b It
Gemma · fernandoruiz
Params1B
Context32K
Smallest0.7 GB
GGUF
GE
Gemma 3 4b It
Gemma · fernandoruiz
Params3.88B
Context128K
Smallest2.4 GB
Vision
GE
Gemma 3 12b It
Gemma · fernandoruiz
Params11.8B
Context128K
Smallest6.9 GB
Vision
SA
Salamandra 7b Instruct
Salamandra · fernandoruiz
Params7.77B
Context8K
Smallest4.6 GB
Coding
IN
InternVL3_5 30B A3B Instruct
Internvl · fernandoruiz
Params11M
Context40K
Smallest0.0 GB
CodingReasoningTool use
GE
Gemma 3 27b It
Gemma · fernandoruiz
Params27B
Context128K
Smallest15.6 GB
Vision
EU
EuroMoE 2.6B A0.6B Instruct 2512
Euromoe · fernandoruiz
Params2.61B
Context32K
Q4_K_M1.6 GB
GGUF
IN
InternVL3_5 30B A3B
Internvl · fernandoruiz
Params30.5B
Context40K
Smallest17.3 GB
GGUF
QW
Qwen3 30B A3B
Qwen · fernandoruiz
Params30.5B
Context40K
Smallest17.3 GB
ReasoningTool use
EU
EuroMoE 2.6B A0.6B Instruct Preview
Euromoe · fernandoruiz
Params2.61B
Context4K
Smallest1.5 GB
GGUF
GE
gemma-2-27b-it
Gemma · fernandoruiz
Params27.2B
Context8K
Smallest15.7 GB
GGUF
PH
Phi 3 mini 4k instruct Q4 K M
Phi · fernandoruiz
Params3.82B
Context4K
Q4_K_M2.4 GB
Coding
GE
gemma-2-27b-it
Gemma · fernandoruiz
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
ME
Medgemma 4b It
Medgemma · fernandoruiz
Params3.88B
Context128K
Smallest2.4 GB
ReasoningVision
EU
EuroMoE 2.6B A0.6B Instruct 2512
Euromoe · fernandoruiz
Params2.61B
Context32K
Smallest1.5 GB
GGUF
MI
Mistral Nemo Instruct 2407
Mistral · fernandoruiz
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ME
Medgemma 27b Text It
Medgemma · fernandoruiz
Params27B
Context128K
Smallest15.6 GB
Reasoning
QW
qwen25 05b multiclinsum distil Q4 0
Qwen · fernandoruiz
Params494M
Context32K
Smallest0.4 GB
Tool use
QW
Qwen3 1.7B Base
Qwen · fernandoruiz
Params1.72B
Context32K
Smallest1.1 GB
ReasoningTool use
QW
Qwen3 30B A6B 16 Extreme
Qwen · fernandoruiz
Params30.5B
Context40K
Smallest17.3 GB
ReasoningTool use
LL
Bio Medical Llama 3 2 1B CoT 012025
Llama · fernandoruiz
Params1.24B
Context128K
Smallest0.8 GB
Tool use
MI
MiMo VL 7B RL
Mimo · fernandoruiz
Params7.62B
Context125K
Smallest4.5 GB
Tool useVision
MA
madlad400 3b mt Q4 K M
Madlad · fernandoruiz
Params2.94B
Context256
Q4_K_M1.9 GB
GGUF
QW
Qwen1.5 MoE A2.7B Chat
Qwen · fernandoruiz
Params14.3B
Context32K
Smallest8.1 GB
GGUF
LL
Llama 3 Physician 8B Instruct
Llama · fernandoruiz
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
SU
SummLlama3.1 8B
Summllama · fernandoruiz
Params8.03B
Context128K
Smallest4.7 GB
Tool use
QW
Josiefied Qwen3 30B A3B Abliterated v2
Qwen · fernandoruiz
Params30.5B
Context40K
Smallest17.3 GB
GGUF
QW
Qwen3 1.7B
Qwen · fernandoruiz
Params2.03B
Context40K
Smallest1.2 GB
ReasoningTool use

About fernandoruiz on Hugging Face

fernandoruiz has published 94 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Llama. The most downloaded are ERNIE 4.5 21B A3B PT, madlad400 3b mt Q4 K S and Gemma 3 1b It.

The quants fernandoruiz publishes most often are Q4_0 (75), Q4_K_M (10) and Q4_K_S (9). Their Q4_K_M files range from 0.7 to 16.6 GB. Parameter counts run from 11M to 46.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has fernandoruiz published?

94 models are listed here, mainly from the Qwen, Gemma and Llama families. The most downloaded is ERNIE 4.5 21B A3B PT.

Which quants does fernandoruiz publish?

The most common are Q4_0 (75 models), Q4_K_M (10 models) and Q4_K_S (9 models).

Keep browsing