GGUF models by Naphula-Archives

55 GGUF models quantized by Naphula-Archives on Hugging Face. Sizes run from 7.24B to 30.7B parameters. The longest trained context is 1048K tokens.

Most downloadedNewestLargestLongest contextSmallest
AS
DarkArtsForge__Asmodeus 24B v2
Asmodeus · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QL
Qliphoth
Qliphoth · Naphula-Archives
Params23.6B
Context128K
Smallest13.4 GB
GGUF
ER
Erebus RP Engine 31B
Erebus · Naphula-Archives
Params30.7B
Context256K
Smallest17.7 GB
ReasoningRoleplayTool use
MI
Sands 12B
Mistral · Naphula-Archives
Params12.2B
Context128K
Smallest13.0 GB
GGUF
MA
Magistaroth 24B v1.2
Magistaroth · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
SL
Slimaki 24B v1.2
Slimaki · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
GE
gemma 4 26B A4B it SOMPOA heresy IQ4 NL
Gemma · Naphula-Archives
Params25.2B
Context256K
Smallest14.6 GB
ReasoningTool use
NA
T13 24B
Naphula · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
AS
Asmodeus 24B v3
Asmodeus · Naphula-Archives
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
FA
Fallen Erebus 8B v0
Fallen · Naphula-Archives
Params8.04B
Context1048K
Smallest8.5 GB
Tool use
ER
Erebus RP Engine 26B A4B Q8 0
Erebus · Naphula-Archives
Params25.2B
Context256K
Smallest26.9 GB
ReasoningRoleplayTool use
DE
DeepWater Pleroma 24B v1
Deepwater · Naphula-Archives
Params23.6B
Context128K
Smallest13.4 GB
GGUF
CY
Cyberdonia 24B v8
Cyberdonia · Naphula-Archives
Params23.6B
Context128K
Smallest13.5 GB
GGUF
QU
Quantum Precog 24B Q8 0
Quantum · Naphula-Archives
Params23.6B
Context128K
Smallest25.1 GB
GGUF
CT
Cthulhu Old Versions Q8 0
Cthulhu · Naphula-Archives
Params23.6B
Context32K
Smallest25.1 GB
GGUF
CY
Cyberdonia 24B v11
Cyberdonia · Naphula-Archives
Params23.6B
Context128K
Smallest25.1 GB
GGUF
AN
Ancient Awakening 12B f16
Ancient · Naphula-Archives
Params12.2B
Context128K
Smallest24.5 GB
GGUF
DR
DrummersDarkFantasyEngine 24B Q6 K
Drummersdarkfantasyengine · Naphula-Archives
Params23.6B
Context128K
Smallest19.3 GB
GGUF
AN
Ancient Awakening 12B MPOA Q8 K XL
Ancient · Naphula-Archives
Params12.2B
Context128K
Smallest14.9 GB
GGUF
GO
Goetia 31B v1
Goetia · Naphula-Archives
Params30.7B
Context256K
Smallest16.9 GB
ReasoningRoleplayTool use
AN
Ancient Awakening 12B Q8 K XL
Ancient · Naphula-Archives
Params12.2B
Context128K
Smallest14.9 GB
GGUF
PI
Piranha 12B v1a Q8 0
Piranha · Naphula-Archives
Params12.2B
Context128K
Smallest13.0 GB
GGUF
MA
magitest mpoa to pdq
Magitest · Naphula-Archives
Params23.6B
Context128K
Smallest19.3 GB
GGUF
RU
G4 Runic Oarfish 26B A4B v1
Runic · Naphula-Archives
Params25.2B
Context256K
Smallest26.9 GB
ReasoningTool use
MI
Naphula Archives__jtatman_mistral_nemo_12b_reasoning_psychology_lora Q6_K GGUF
Mistral · Naphula-Archives
Params12.2B
Context128K
Smallest10.1 GB
Reasoning
NE
Nemo karcher23 test 12B Q6 K
Nemo · Naphula-Archives
Params12.2B
Context128K
Smallest10.1 GB
GGUF
SA
Savage Sands 12B
Savage · Naphula-Archives
Params12.2B
Context128K
Smallest13.0 GB
GGUF
AN
Ancient Awakening 12B MPOA f16
Ancient · Naphula-Archives
Params12.2B
Context128K
Smallest24.5 GB
GGUF
SA
Salamander 24B v1
Salamander · Naphula-Archives
Params23.6B
Context128K
Smallest13.4 GB
GGUF
NU
NUSLERP test3 12B
Nuslerp · Naphula-Archives
Params12.2B
Context128K
Smallest13.0 GB
GGUF

About Naphula-Archives on Hugging Face

Naphula-Archives has published 55 GGUF models that ggufmodels.com tracks, across families such as Mistral, Ancient and Runic. The most downloaded are DarkArtsForge__Asmodeus 24B v2, Qliphoth and Erebus RP Engine 31B.

The quants Naphula-Archives publishes most often are Q8_0 (21), IQ4_XS (12), Q6_K (11) and Q4_0 (9). Their Q4_K_M files range from 5.8 to 14.3 GB. Parameter counts run from 7.24B to 30.7B, and the longest trained context window is 1048K tokens.

Frequently asked questions

What GGUF models has Naphula-Archives published?

55 models are listed here, mainly from the Mistral, Ancient and Runic families. The most downloaded is DarkArtsForge__Asmodeus 24B v2.

Which quants does Naphula-Archives publish?

The most common are Q8_0 (21 models), IQ4_XS (12 models), Q6_K (11 models) and Q4_0 (9 models).

Keep browsing