Behemoth GGUF models

107 GGUF models in the Behemoth family, quantized by 9 uploaders. Sizes run from 3.09B to 195B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
BE
Behemoth 128B v3
Behemoth · bartowski
Params125B
Context256K
Q4_K_M78.4 GB
GGUF
BE
Behemoth X 123B v2.2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M76.3 GB
GGUF
BE
Behemoth X 123B v2.2
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth X 123B v2.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth X 123B v2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth T1 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
Behemoth 123B v1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth 128B v3
Behemoth · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
ReasoningTool use
BE
Behemoth R1 123B v2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Reasoning
BE
Behemoth ReduX 123B v1.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Tool use
BE
Behemoth X R1 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
Behemoth 123B v2.2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth 123B v2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth ReduX 123B v1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Tool use
BE
Behemoth OpusX 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
OR1 Behemoth
Behemoth · mradermacher
Params72.7B
Context40K
Q4_K_M47.4 GB
CodingReasoning
BE
Behemoth OpusX 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
Overthinking Rustacean Behemoth
Behemoth · mradermacher
Params72.7B
Context40K
Q4_K_M47.4 GB
CodingReasoning
BE
Behemoth 123B v2.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth 123B v2.2
Behemoth · TheDrummer
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth X 123B v2.2
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
GGUF
BE
Behemoth 123B v1.2
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Tool use
BE
Behemoth 123B v1.1
Behemoth · bartowski
Params123B
Context128K
Q4_K_M73.2 GB
Tool use
BE
Overthinking Rustacean Behemoth
Behemoth · mradermacher
Params72.7B
Context40K
Q4_K_M47.4 GB
CodingReasoning
BE
Behemoth T1 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
Behemoth X R1 123B
Behemoth · mradermacher
Params123B
Context128K
Q4_K_M73.2 GB
ReasoningRoleplay
BE
Behemoth 3B 070225 Post0.1
Behemoth · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
BE
OR1 Behemoth
Behemoth · mradermacher
Params72.7B
Context40K
Q4_K_M47.4 GB
CodingReasoning
BE
Behemoth X 123B v2 i1
Behemoth · mradermacher
Params123B
Context128K
Smallest0.0 GB
GGUF
BE
Behemoth 123B v1.1 i1
Behemoth · mradermacher
Params123B
Context128K
Smallest26.0 GB
Tool use

About the Behemoth GGUF models

Behemoth is represented on ggufmodels.com by 107 GGUF models, quantized by 9 uploaders on Hugging Face. The most downloaded are Behemoth 128B v3, Behemoth X 123B v2.2 and Behemoth X 123B v2.2. Parameter counts run from 3.09B to 195B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Behemoth model is between 1.9 to 78.4 GB, which is the quant most people start with. Most files come from mradermacher (56), BeaverAI (24) and bartowski (13). The quants you will meet most often are Q2_K (86), Q4_K_M (67), Q5_K_M (56) and Q3_K_M (54), where the number is how many models offer that quant.

Frequently asked questions

Which Behemoth GGUF should I download?

The most downloaded Behemoth GGUF here is Behemoth 128B v3. 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 Behemoth model need?

Q4_K_M files of Behemoth models on this site range from 1.9 to 78.4 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 Behemoth GGUF files come from?

The most common quantizers here are mradermacher, BeaverAI and bartowski. 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