GGUF models by yamatazen

46 GGUF models quantized by yamatazen on Hugging Face. Sizes run from 4.02B to 23.6B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
GE
Gemma2 Snowflakes 9B
Gemma · yamatazen
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
QW
Qwen3 4B Instruct 2507 Heretic
Qwen · yamatazen
Params4.02B
Context256K
Q4_K_M2.5 GB
GGUF
MI
Shisa v2 Mistral Nemo 12B Abliterated
Mistral · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
ET
EtherealAurora 12B
Etherealaurora · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GE
Gemma2 Alicia 9B Q4 K M
Gemma · yamatazen
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
HI
Himeyuri Magnum 12B HereticLoRA Q4 K M
Himeyuri · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ET
EtherealAurora 12B Lorablated Q4 K M
Etherealaurora · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
Orion Qwen3 4B CPT v2605
Qwen · yamatazen
Params4.02B
Context32K
Q4_K_M2.5 GB
GGUF
AU
Aurora SCE 12B Q4 K M
Aurora · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
HI
Himeyuri Magnum 12B v2
Himeyuri · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
TW
Twilight SCE 12B v2
Twilight · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
ET
EtherealMoon 12B Q4 K M
Etherealmoon · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
ES
EsotericKnowledge 24B
Esotericknowledge · yamatazen
Params23.6B
Context32K
Smallest11.5 GB
GGUF
GE
Gemma2 Evelyn 9B
Gemma · yamatazen
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
TW
Twilight SCE 12B
Twilight · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
HI
Himeyuri Magnum 12B HereticMerge
Himeyuri · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
NI
NightWind 12B Q4 K M
Nightwind · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
LO
LoyalMaid 12B Q4 K M
Loyalmaid · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
AM
Amelia SCE 12B Q4 K M
Amelia · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
BL
BlueLight 12B
Bluelight · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
SN
SnowElf 12B
Snowelf · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
ET
EtherealNight 12B Q4 K M
Etherealnight · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
HM
HMS Slerp 12B v2
Hms · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
QW
Qwen3 V Science 14B v2
Qwen · yamatazen
Params14.8B
Context32K
Q4_K_M9.0 GB
ReasoningTool use
EL
ElvenMaid 12B v3
Elvenmaid · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
HI
Himeyuri Magnum 12B Q4 K M
Himeyuri · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
GO
L3 GothicMaid Upscaled 11B Q4 K M
Gothicmaid · yamatazen
Params11.5B
Context8K
Q4_K_M7.0 GB
GGUF
ST
StarrySky 12B
Starrysky · yamatazen
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
PE
PerpetualNight 12B Q4 K M
Perpetualnight · yamatazen
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
QW
Qwen3 V Science 14B
Qwen · yamatazen
Params14.8B
Context32K
Q4_K_M9.0 GB
ReasoningTool use

About yamatazen on Hugging Face

yamatazen has published 46 GGUF models that ggufmodels.com tracks, across families such as Etherealaurora, Qwen and Himeyuri. The most downloaded are Gemma2 Snowflakes 9B, Qwen3 4B Instruct 2507 Heretic and Shisa v2 Mistral Nemo 12B Abliterated.

The quants yamatazen publishes most often are Q4_K_M (45) and Q3_K_M (1). Their Q4_K_M files range from 2.5 to 12.4 GB. Parameter counts run from 4.02B to 23.6B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has yamatazen published?

46 models are listed here, mainly from the Etherealaurora, Qwen and Himeyuri families. The most downloaded is Gemma2 Snowflakes 9B.

Which quants does yamatazen publish?

The most common are Q4_K_M (45 models) and Q3_K_M (1 models).

Keep browsing