GGUF models by EloyOn

40 GGUF models quantized by EloyOn on Hugging Face. Sizes run from 4.51B to 36.2B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
IM
Impish_Bloodmoon_12B_Abliterated
Impish · EloyOn
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
GE
Gemma 3 27b It Abliterated
Gemma · EloyOn
Params27B
Context128K
Smallest18.8 GB
Vision
LO
M3.2 24B Loki V1.3
Loki · EloyOn
Params23.6B
Context128K
Smallest16.3 GB
GGUF
SE
Sexpedition MS3.2 24B
Sexpedition · EloyOn
Params23.6B
Context128K
Smallest16.3 GB
GGUF
NE
Neona 12B
Neona · EloyOn
Params12.2B
Context128K
Smallest7.1 GB
GGUF
SE
Seed OSS 36B Erotic
Seed · EloyOn
Params36.2B
Context512K
Smallest25.0 GB
GGUF
HE
Hermes 4.3 36B
Hermes · EloyOn
Params36.2B
Context512K
Smallest25.0 GB
ReasoningRoleplayTool use
CY
Cydonia 24B v4.3
Cydonia · EloyOn
Params23.6B
Context128K
Smallest16.3 GB
GGUF
QW
Huihui Qwen3 VL 32B Thinking Abliterated
Qwen · EloyOn
Params32.8B
Context256K
Smallest22.6 GB
ReasoningTool useVision
CH
Christian Bible Expert v2.0 24B
Christian · EloyOn
Params23.6B
Context32K
Smallest16.3 GB
GGUF
MI
Ministrations 8B v1 Q4 K M
Ministrations · EloyOn
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
GL
GLM 4 32B 0414
GLM · EloyOn
Params32.6B
Context32K
Smallest22.5 GB
Tool use
PH
Phi 4 Heretic
Phi · EloyOn
Params14.7B
Context16K
Smallest10.2 GB
Coding
MA
Magidonia 24B v4.3
Magidonia · EloyOn
Params23.6B
Context128K
Smallest16.3 GB
GGUF
CH
Christian Bible Expert v2.0 12B
Christian · EloyOn
Params12.2B
Context128K
Smallest8.5 GB
Tool use
SN
Snowpiercer 15B v1
Snowpiercer · EloyOn
Params15B
Context64K
Smallest10.4 GB
GGUF
LL
Impish LLAMA 4B Q5 0
Llama · EloyOn
Params4.51B
Context128K
Smallest3.2 GB
GGUF
MI
Mira v1.21 27B Rlvr
Mira · EloyOn
Params27B
Context128K
Smallest18.8 GB
GGUF
LU
L3 8B Lunaris v1 Q5 0
Lunaris · EloyOn
Params8.03B
Context8K
Smallest5.6 GB
GGUF
BI
Big Alice 28B v1
Big · EloyOn
Params28.6B
Context64K
Smallest19.8 GB
GGUF
SY
Synthia S1 27b
Synthia · EloyOn
Params27B
Context128K
Smallest18.8 GB
GGUF
WI
Wingless_Imp_8B
Wingless · EloyOn
Params8.03B
Context128K
Smallest5.6 GB
GGUF
NE
NemoMix Unleashed 12B Q5 0
Nemomix · EloyOn
Params12.2B
Context1000K
Smallest8.5 GB
GGUF
KR
Krix 12B Model_Stock
Krix · EloyOn
Params12.2B
Context1000K
Smallest7.1 GB
GGUF
ST
L3 8B Stheno v3.2 Q5 0
Stheno · EloyOn
Params8.03B
Context8K
Smallest5.6 GB
GGUF
IM
Impish_Nemo_12B
Impish · EloyOn
Params12.2B
Context1000K
Smallest8.5 GB
GGUF
BE
Beepo 22B
Beepo · EloyOn
Params22.2B
Context32K
Smallest12.6 GB
Tool use
QW
Qwen3 Gutenberg Encore 14B
Qwen · EloyOn
Params14.8B
Context32K
Smallest10.3 GB
ReasoningTool use
VI
Violet Twilight v0.2 Q5 0
Violet · EloyOn
Params12.2B
Context1000K
Smallest8.5 GB
Roleplay
LY
MN 12B Lyra v4
Lyra · EloyOn
Params12.2B
Context1000K
Smallest8.5 GB
Tool use

About EloyOn on Hugging Face

EloyOn has published 40 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and Impish. The most downloaded are Impish_Bloodmoon_12B_Abliterated, Gemma 3 27b It Abliterated and M3.2 24B Loki V1.3.

The quants EloyOn publishes most often are Q5_0 (35), Q4_K_M (2), Q4_0 (2) and Q4_K_S (1). Their Q4_K_M files range from 4.9 to 7.5 GB. Parameter counts run from 4.51B to 36.2B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has EloyOn published?

40 models are listed here, mainly from the Qwen, Phi and Impish families. The most downloaded is Impish_Bloodmoon_12B_Abliterated.

Which quants does EloyOn publish?

The most common are Q5_0 (35 models), Q4_K_M (2 models), Q4_0 (2 models) and Q4_K_S (1 models).

Keep browsing