GGUF models by hardlyworking

37 GGUF models quantized by hardlyworking on Hugging Face. Sizes run from 4.02B to 32.8B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
QW
Qwen3 32B Biprojected Norm Preserving Abliterated
Qwen · hardlyworking
Params32.8B
Context40K
Q4_K_M19.8 GB
GGUF
BR
4Brp Q4 0
Brp · hardlyworking
Params4.41B
Context256K
Smallest2.6 GB
GGUF
SE
Secret4B
Secret · hardlyworking
Params4.02B
Context32K
Smallest3.3 GB
GGUF
QW
RpR v4 Fast 30B A3B
Qwen · hardlyworking
Params30.5B
Context40K
Smallest17.5 GB
ReasoningTool use
SU
Sugma4B
Sugma · hardlyworking
Params4.02B
Context32K
Smallest3.3 GB
ReasoningTool use
RA
Ramen 12B
Ramen · hardlyworking
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
AU
Aura_24B
Aura · hardlyworking
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
MI
BabyBoo9B
Mike · hardlyworking
Params10.7B
Context256K
Smallest6.1 GB
GGUF
GO
Goldenworking
Goldenworking · hardlyworking
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
AU
Aura_24B
Aura · hardlyworking
Params23.6B
Context128K
Smallest19.3 GB
GGUF
ME
MS32 Merged
Merged · hardlyworking
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
NO
Noodles Merge 12B
Noodles · hardlyworking
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
HO
moooooo
Holdmy · hardlyworking
Params4.41B
Context256K
Smallest2.6 GB
GGUF
RA
Ramen 12B
Ramen · hardlyworking
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
GO
Golden Curry 12B
Golden · hardlyworking
Params12.2B
Context1000K
Smallest6.1 GB
Tool use
MI
proto9B
Mike · hardlyworking
Params10.7B
Context256K
Smallest6.1 GB
GGUF
AF
AFM 4.5B Preview
Afm · hardlyworking
Params4.62B
Context64K
Smallest2.7 GB
GGUF
RA
Ramen 12B
Ramen · hardlyworking
Params12.2B
Context1000K
Smallest6.1 GB
GGUF
FI
Final4BRC
Final · hardlyworking
Params4.41B
Context256K
Smallest4.7 GB
GGUF
FI
Final4BRC3
Final · hardlyworking
Params4.41B
Context256K
Smallest4.7 GB
GGUF
ME
MediusMerge
Mediusmerge · hardlyworking
Params14.8B
Context128K
Smallest6.7 GB
Tool use
AU
Austral 4.5B Winton
Austral · hardlyworking
Params4.62B
Context64K
Smallest2.7 GB
GGUF
FI
Final4BRC3
Final · hardlyworking
Params4.41B
Context256K
Smallest2.6 GB
GGUF
AU
Aura_Half_24B
Aura · hardlyworking
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
BT
4BTestRC
Btestrc · hardlyworking
Params4.41B
Context256K
Smallest4.7 GB
GGUF
FI
Firestarter
Firestarter · hardlyworking
Params30.5B
Context32K
Smallest17.5 GB
GGUF
BR
Broth 12B
Broth · hardlyworking
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
BT
RepRemove4B
Btestrc · hardlyworking
Params4.41B
Context256K
Smallest4.7 GB
GGUF
XG
Xgen Small 4B Instruct R
Xgen · hardlyworking
Params4.41B
Context256K
Smallest2.6 GB
GGUF
BR
4Brepremover
Brepremover · hardlyworking
Params4.41B
Context256K
Smallest2.6 GB
GGUF

About hardlyworking on Hugging Face

hardlyworking has published 37 GGUF models that ggufmodels.com tracks, across families such as Final, Ramen and Holdmy. The most downloaded are Qwen3 32B Biprojected Norm Preserving Abliterated, 4Brp Q4 0 and Secret4B.

The quants hardlyworking publishes most often are Q4_0 (14), Q4_K_S (7), Q8_0 (6) and Q4_K_M (4). Their Q4_K_M files range from 14.3 to 19.8 GB. Parameter counts run from 4.02B to 32.8B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has hardlyworking published?

37 models are listed here, mainly from the Final, Ramen and Holdmy families. The most downloaded is Qwen3 32B Biprojected Norm Preserving Abliterated.

Which quants does hardlyworking publish?

The most common are Q4_0 (14 models), Q4_K_S (7 models), Q8_0 (6 models) and Q4_K_M (4 models).

Keep browsing