GGUF models by jnjj

35 GGUF models quantized by jnjj on Hugging Face. Sizes run from 4M to 3.88B parameters. The longest trained context is 1280000K tokens.

Most downloadedNewestLargestLongest contextSmallest
JN
xd v2
Jnjj · jnjj
Params13M
Context2K
Q4_K_M0.0 GB
GGUF
GE
Gemma 3 4b It Qat Int4 Quantized Inference Unrestricted Weights Only Sf
Gemma · jnjj
Params2.28B
Context128K
Smallest3.8 GB
GGUF
GE
Gemma 3 1b It Qat Q4_0 Quantized Inference Extreme Shrinkage Sf
Gemma · jnjj
Params651M
Context32K
Smallest1.0 GB
GGUF
GE
Gemma 3 1b It Qat Int4 Quantized Inference Extreme Shrinkage Sf
Gemma · jnjj
Params651M
Context32K
Smallest1.0 GB
GGUF
GE
Gemma 3 1b It Qat Q4_0 Unquantized
Gemma · jnjj
Params1B
Context32K
Smallest0.7 GB
GGUF
GE
Gemma 3 1b It Qat Int4 Quantized Less Restricted Filtered Sf
Gemma · jnjj
Params651M
Context32K
Smallest1.0 GB
GGUF
MO
My Model
Model · jnjj
Params13M
Context1K
Smallest0.0 GB
GGUF
MO
model
jnjj
Params13M
Context2K
Q4_K_M0.0 GB
GGUF
QW
Model_No_Bias_Qwen3 0.6B
Qwen · jnjj
Params596M
Context40K
Smallest0.4 GB
GGUF
LL
Bitnet Llama
Llama · jnjj
Params25M
Context256
Smallest0.0 GB
Tool use
QW
vvcvc
Qwen · jnjj
Params752M
Context40K
Smallest0.8 GB
ReasoningTool use
GE
gxgcjc
Gemma · jnjj
Params953M
Context32K
Smallest1.2 GB
GGUF
QW
Qwen3 0.6B
Qwen · jnjj
Params596M
Context40K
Smallest0.3 GB
ReasoningTool use
GE
Gemma 3 4b It 1layer Actual
Gemma · jnjj
Params3.88B
Context1280000K
Smallest1.7 GB
GGUF
MO
Model_13M
Model · jnjj
Params13M
Context1K
Smallest0.0 GB
ReasoningTool use
XD
Xddchvh
Xddchvh · jnjj
Params1B
Context32K
Smallest0.7 GB
GGUF
QW
Model_No_Bias_Qwen3 0.6B
Qwen · jnjj
Params596M
Context40K
Smallest0.3 GB
ReasoningTool use
MO
My Model
Model · jnjj
Params13M
Context1K
Smallest0.0 GB
GGUF
XD
xdfdfdfdfddd Q2 K
Xdfdfdfdfddd · jnjj
Params3.21B
Context128K
Smallest1.4 GB
Tool use
UN
Unsloth_Xd
Unsloth · jnjj
Params651M
Context32K
Smallest1.0 GB
GGUF
IN
Instruction Unified Model
Instruction · jnjj
Params13M
Context1K
Smallest0.0 GB
GGUF
CC
ccvcvc
Ccvcvc · jnjj
Params752M
Context129K
Smallest0.3 GB
ReasoningTool use
QW
Gvv
Qwen · jnjj
Params596M
Context40K
Smallest0.3 GB
ReasoningTool use
FG
fgfgfg
Fgfgfg · jnjj
Params596M
Context40K
Smallest0.6 GB
ReasoningTool use
MY
my v8 Q2 K
jnjj
Params945M
Context87891K
Smallest0.5 GB
Tool use
ZC
zczczczcz
Zczczczcz · jnjj
Params1B
Context977K
Smallest1.0 GB
GGUF
MU
multi-dataset-model
Multi · jnjj
Params13M
Context1K
Smallest0.0 GB
GGUF
CV
cvcvcvcv
Cvcvcvcv · jnjj
Params1B
Context1K
Smallest0.7 GB
GGUF
VC
vcvcvcv
Vcvcvcv · jnjj
Params3.88B
Context128K
Smallest3.2 GB
Vision
SI
Single Layer Repo
Single · jnjj
Params394M
Context128K
Smallest0.3 GB
Tool use

About jnjj on Hugging Face

jnjj has published 35 GGUF models that ggufmodels.com tracks, across families such as Gemma, Qwen and Model. The most downloaded are xd v2, Gemma 3 4b It Qat Int4 Quantized Inference Unrestricted Weights Only Sf and Gemma 3 1b It Qat Q4_0 Quantized Inference Extreme Shrinkage Sf.

The quants jnjj publishes most often are Q2_K (18), Q3_K_L (6), Q8_0 (4) and Q4_0 (3). Their Q4_K_M files range from 0.0 to 0.0 GB. Parameter counts run from 4M to 3.88B, and the longest trained context window is 1280000K tokens.

Frequently asked questions

What GGUF models has jnjj published?

35 models are listed here, mainly from the Gemma, Qwen and Model families. The most downloaded is xd v2.

Which quants does jnjj publish?

The most common are Q2_K (18 models), Q3_K_L (6 models), Q8_0 (4 models) and Q4_0 (3 models).

Keep browsing