Goetia GGUF models

83 GGUF models in the Goetia family, quantized by 17 uploaders. Sizes run from 11M to 30.7B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
GO
Goetia 26B A4B v1.7
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
GO
Goetia 26B A4B v1.3 Absolute Heretic ARA
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
GO
Goetia 26B A4B v1.7
Goetia · bartowski
Params26B
Context256K
Q4_K_M18.8 GB
Roleplay
GO
Goetia 24B v1.4 Heretic
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GO
Goetia 26B A4B v1.3 Absolute Heretic ARA
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
GO
Goetia 26B A4B v1.7
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
GO
Goetia 26B A4B v1.6
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
GO
Goetia 26B A4B v1.5
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
GO
Naphula Goetia 26B A4B v1.7 APEX
Goetia · Koshkasa
Params26B
Context256K
Q4_K_M17.4 GB
Roleplay
GO
Goetia 26B A4B v1.3
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
GO
Goetia 8B v1
Goetia · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Roleplay
GO
Goetia 31B v1
Goetia · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
GO
Goetia 24B v1.1
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
GO
Goetia 24B v1.3 Absolute Heresy
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GO
Goetia 26B A4B v1.4
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
GO
Goetia 24B v1.4
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
RoleplayTool use
GO
Goetia 26B A4B v1.4 LazyLora Heresy
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
GO
Goetia 24B v1.3
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GO
Goetia 26B A4B v1.4 LazyLora Heresy Heretic
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GO
Goetia 31B v1
Goetia · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
GO
Goetia 24B v1.2 Absolute Heresy
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GO
Goetia 26B A4B v1.3 Tainted Heretic ARI
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GO
Goetia 26B A4B v1.6
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
GO
Goetia 26B A4B v1.4
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
GO
Goetia 24B v1.4
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
RoleplayTool use
GO
Goetia 26B A4B v1.4 SOMPOA Heresy
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GO
Goetia 24B v1.2
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GO
Goetia 24B v1.4 Heretic
Goetia · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
RoleplayTool use
GO
Goetia 26B A4B v1.7
Goetia · npario
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
GO
Goetia 26B A4B v1.3
Goetia · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use

About the Goetia GGUF models

Goetia is represented on ggufmodels.com by 83 GGUF models, quantized by 17 uploaders on Hugging Face. The most downloaded are Goetia 26B A4B v1.7, Goetia 26B A4B v1.3 Absolute Heretic ARA and Goetia 26B A4B v1.7. Parameter counts run from 11M to 30.7B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Goetia model is between 4.9 to 18.8 GB, which is the quant most people start with. Most files come from mradermacher (42), seeingterra (7) and Phil2Sat (5). The quants you will meet most often are Q6_K (52), Q4_K_M (52), IQ4_XS (50) and Q5_K_M (49), where the number is how many models offer that quant.

Frequently asked questions

Which Goetia GGUF should I download?

The most downloaded Goetia GGUF here is Goetia 26B A4B v1.7. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Goetia model need?

Q4_K_M files of Goetia models on this site range from 4.9 to 18.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Goetia GGUF files come from?

The most common quantizers here are mradermacher, seeingterra and Phil2Sat. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing