The GGUF models

116 GGUF models in the The family, quantized by 33 uploaders. Sizes run from 2M to 70.6B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TH
The Trinity Coder 7B
The · RichardErkhov
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
TH
MS3.2 The Omega Directive 24B Unslop v2.0
The · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
TH
The_Elder v2
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TH
The Trinity Coder 7B
The · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoning
TH
The True Abomination 24B
The · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
TH
The_Elder
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TH
MS3.2 The Omega Directive 24B Unslop v2.1
The · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
TH
The Omega Abomination M 12B v1.0
The · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
Tool use
TH
The Functionary 12B
The · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Tool use
TH
L3.3 The Omega Directive 70B Unslop v2.1
The · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
TH
The Omega Directive M 12B v1.0
The · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
TH
On the Strange Lands MN 12B
The · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
TH
The Omega Directive M 12B v1.0
The · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
TH
Mn 12b The Yapper
The · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
TH
The_Elder
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TH
The Omega Directive M 24B v1.1
The · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
TH
The Omega Directive M 12B Unslop v2.0
The · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
TH
The Omega Directive M 8B v1.0
The · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
TH
L3.3 The Omega Directive 70B Unslop v2.0 i1
The · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
TH
The Omega Legion L 70B v1.0
The · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Tool use
TH
The Trinity Coder 7B
The · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoning
TH
The Omega Directive M 12B Unslop v2.0
The · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
Roleplay
TH
The Omega Abomination M 24B v1.1
The · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
TH
The Omega Abomination L 70B v1.0
The · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
TH
The_Creeping_Darkness X2 16B
The · mradermacher
Params16.3B
Context128K
Q4_K_M9.9 GB
Tool use
TH
The Omega Directive M 8B v1.0
The · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
TH
The_Dealer 3.2 1B
The · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
Roleplay
TH
The_Croupier 3.2 1B
The · mradermacher
Params1.5B
Context128K
Q4_K_M1.0 GB
Roleplay
TH
The_Elder v2
The · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
TH
The_Dead_Ripper 3.2 1B
The · mradermacher
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use

About the The GGUF models

The is represented on ggufmodels.com by 116 GGUF models, quantized by 33 uploaders on Hugging Face. The most downloaded are The Trinity Coder 7B, MS3.2 The Omega Directive 24B Unslop v2.0 and The_Elder v2. Parameter counts run from 2M to 70.6B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a The model is between 0.1 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (77), HigherMind (4) and ineosnexus (2). The quants you will meet most often are Q4_K_M (93), Q4_K_S (83), Q5_K_M (82) and IQ4_XS (82), where the number is how many models offer that quant.

Frequently asked questions

Which The GGUF should I download?

The most downloaded The GGUF here is The Trinity Coder 7B. 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 The model need?

Q4_K_M files of The models on this site range from 0.1 to 42.5 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 The GGUF files come from?

The most common quantizers here are mradermacher, HigherMind and ineosnexus. 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