GGUF models by gguf-org
43 GGUF models quantized by gguf-org on Hugging Face. Sizes run from 2M to 27.9B parameters. The longest trained context is 256K tokens.
IM
z image
Image · gguf-org
Params84M
Context—
Q4_K_M4.5 GB
KR
krea 2
Krea · gguf-org
Params12.8B
Context—
Smallest0.3 GB
FL
flux2 dev
Flux · gguf-org
Params17.8B
Context—
Q4_K_M20.0 GB
FA
fastvlm
Fastvlm · gguf-org
Params759M
Context—
Q4_K_M1.4 GB
QW
qwen image 2.1
Qwen · gguf-org
Params338M
Context256K
Q4_K_M5.0 GB
TE
tensor bank
Tensor · gguf-org
Params—
Context—
Q4_K_M0.0 GB
GE
Gemma 3 270m It
Gemma · gguf-org
Params268M
Context32K
Q4_K_M0.3 GB
FA
Fara 7B
Fara · gguf-org
Params7.62B
Context125K
Q4_K_M4.7 GB
VI
vibevoice
Vibevoice · gguf-org
Params2.7B
Context—
Q4_K_M3.5 GB
GE
Gemma 3 1b It
Gemma · gguf-org
Params1B
Context32K
Q4_K_M0.8 GB
GE
Gemma 3 270m
Gemma · gguf-org
Params268M
Context32K
Q4_K_M0.3 GB
FL
flux dev
Flux · gguf-org
Params123M
Context—
Q4_K_M6.7 GB
ST
sd3.5 large
Stable · gguf-org
Params695M
Context—
Smallest0.2 GB
LT
ltx2
Ltx · gguf-org
Params11.8B
Context128K
Smallest4.8 GB
GE
Gemma 3 1b Pt
Gemma · gguf-org
Params1B
Context32K
Q4_K_M0.8 GB
GR
docling
Granite · gguf-org
Params258M
Context—
Q4_K_M0.5 GB
FL
flux kontext
Flux · gguf-org
Params11.9B
Context—
Q4_K_M6.9 GB
HO
holo
Holo · gguf-org
Params4.07B
Context—
Q4_K_M4.1 GB
MO
moss image
Moss · gguf-org
Params5.08B
Context—
Smallest3.5 GB
IR
iris 3b
Iris · gguf-org
Params2.99B
Context—
Smallest2.5 GB
LE
lens
Lens · gguf-org
Params4.1B
Context—
Smallest0.2 GB
LT
ltx2.3
Ltx · gguf-org
Params1.16B
Context—
Smallest0.7 GB
SQ
t2sql
Sql · gguf-org
Params4.02B
Context40K
Q4_K_M0.4 GB
GE
gemma 4 e2b it
Gemma · gguf-org
Params4.65B
Context128K
Smallest3.0 GB
FL
flux3 image klein
Flux · gguf-org
Params5.55B
Context—
Smallest0.2 GB
MA
mageflow
Mage · gguf-org
Params4.12B
Context—
Smallest0.3 GB
QU
quant type
Quant · gguf-org
Params—
Context—
Q4_K_M0.0 GB
MI
ming image
Ming · gguf-org
Params6.15B
Context—
Smallest0.3 GB
CH
chat
Chat · gguf-org
Params1B
Context32K
Smallest0.7 GB
MU
muse glimmer 30b
Muse · gguf-org
Params27.9B
Context128K
Smallest1.5 GB
About gguf-org on Hugging Face
gguf-org has published 43 GGUF models that ggufmodels.com tracks, across families such as Gemma, Flux and Qwen. The most downloaded are z image, krea 2 and flux2 dev.
The quants gguf-org publishes most often are F16 (25), Q4_0 (24), Q8_0 (21) and Q2_K (18). Their Q4_K_M files range from 0.0 to 20.0 GB. Parameter counts run from 2M to 27.9B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has gguf-org published?
43 models are listed here, mainly from the Gemma, Flux and Qwen families. The most downloaded is z image.
Which quants does gguf-org publish?
The most common are F16 (25 models), Q4_0 (24 models), Q8_0 (21 models) and Q2_K (18 models).