GGUF models by kainatq

34 GGUF models quantized by kainatq on Hugging Face. Sizes run from 7.24B to 14.8B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
HE
Kainaticulous Rp 7b
Hexoteric · kainatq
Params7.24B
Context32K
Q4_K_M4.4 GB
Roleplay
KS
Ksong 1 12b_v1
Ksong · kainatq
Params10.1B
Context1000K
Q4_K_M6.2 GB
GGUF
AZ
Kaiden Sakura Violet Square Azura crimson 12B Q4 K M
Azure · kainatq
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
AZ
Kaiden Sakura Violet Square Azura crimson 12B Q3 K L
Azure · kainatq
Params12.2B
Context1000K
Smallest6.6 GB
GGUF
KI
Kinggaroo 12b v1
Kinggaroo · kainatq
Params12.2B
Context1000K
Smallest6.1 GB
GGUF
KA
KaidenRp2400_12b_v1
Kaidenrp · kainatq
Params12.2B
Context128K
Smallest6.6 GB
GGUF
AZ
Kaiden Sakura Violet Square Azura crimson 12B Q5 K M
Azure · kainatq
Params12.2B
Context1000K
Smallest8.7 GB
GGUF
KI
RP King 12b II
King · kainatq
Params12.2B
Context1000K
Q4_K_M7.5 GB
Roleplay
KI
KingRoleplay_12b_v1_t
Kingroleplay · kainatq
Params12.2B
Context128K
Smallest6.6 GB
Roleplay
KO
Koder Quantum 14b
Koder · kainatq
Params14.8B
Context32K
Smallest6.7 GB
Tool use
KP
Kpt 7b v 0.2 Q6 K
Kpt · kainatq
Params7.24B
Context32K
Smallest5.9 GB
GGUF
KA
Kaiden gang 12B Q3 K M
Kaiden · kainatq
Params12.2B
Context1000K
Smallest6.1 GB
Tool use
KA
Kainat S Elite 14b T1
Kainat · kainatq
Params14.8B
Context128K
Q4_K_M9.0 GB
ReasoningTool use
TE
test002 Q6 K
Test · kainatq
Params7.24B
Context32K
Smallest5.9 GB
GGUF
KP
KPM 7b v0.1 Q4 K M
Kpm · kainatq
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
AZ
Kaiden Sakura Violet Square Azura crimson 12B Q3 K M
Azure · kainatq
Params12.2B
Context1000K
Smallest6.1 GB
GGUF
KP
KPT 7b v0.3 Q4 K M
Kpt · kainatq
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QU
Quantum Keek v2 7b
Quantum · kainatq
Params7.61B
Context128K
Q4_K_M4.7 GB
GGUF
KI
RP King 12b
King · kainatq
Params12.2B
Context1000K
Smallest6.1 GB
Roleplay
KP
KPT 7b v0.2 stock Q6 K
Kpt · kainatq
Params7.24B
Context32K
Smallest5.9 GB
GGUF
KA
Kairos 14B Base_v1
Kairos · kainatq
Params14.8B
Context32K
Smallest7.3 GB
GGUF
KP
Kpt 7b v 0.2 Q5 K M
Kpt · kainatq
Params7.24B
Context32K
Smallest5.1 GB
GGUF
KO
Koder Quantum 14b
Koder · kainatq
Params14.8B
Context32K
Smallest7.3 GB
Tool use
KI
KingRoleplay_12b_v1
Kingroleplay · kainatq
Params12.2B
Context128K
Smallest6.6 GB
Roleplay
KP
KPRA 7b Q4 K M
Kpra · kainatq
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QU
Quantum Keek 7b
Quantum · kainatq
Params7.61B
Context128K
Q4_K_M4.7 GB
Tool use
KI
Kinggaroo 12b v2
Kinggaroo · kainatq
Params12.2B
Context1000K
Smallest6.1 GB
GGUF
KP
Kpt 7b test Q6 K
Kpt · kainatq
Params7.24B
Context32K
Smallest5.9 GB
GGUF
KO
Koder Quantum 14b
Koder · kainatq
Params14.8B
Context32K
Smallest5.8 GB
Tool use
QU
Quantum Keek 7b
Quantum · kainatq
Params7.61B
Context128K
Smallest3.5 GB
Tool use

About kainatq on Hugging Face

kainatq has published 34 GGUF models that ggufmodels.com tracks, across families such as Kpt, Azure and Quantum. The most downloaded are Kainaticulous Rp 7b, Ksong 1 12b_v1 and Kaiden Sakura Violet Square Azura crimson 12B Q4 K M.

The quants kainatq publishes most often are Q4_K_M (11), Q3_K_M (8), Q3_K_L (6) and Q6_K (4). Their Q4_K_M files range from 4.4 to 9.0 GB. Parameter counts run from 7.24B to 14.8B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has kainatq published?

34 models are listed here, mainly from the Kpt, Azure and Quantum families. The most downloaded is Kainaticulous Rp 7b.

Which quants does kainatq publish?

The most common are Q4_K_M (11 models), Q3_K_M (8 models), Q3_K_L (6 models) and Q6_K (4 models).

Keep browsing