LLM EXPLORER 58,975 MODELS INDEXED

Behemoth 128B V3 by TheDrummer

By TheDrummer · 19 downloads
HF Repo ↗ Copy URL

Behemoth 128B V3 is an open-source language model by TheDrummer. Features: 128b LLM, VRAM: 248.5GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.32.

Base model:finetune:mistralai/... Base model:mistralai/mistral-m...   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheDrummer/Behemoth-128B-v3 

Behemoth 128B V3 Parameters and Internals

LLM NameBehemoth 128B V3
Repository 🤗https://huggingface.co/TheDrummer/Behemoth-128B-v3 
Base Model(s)  mistralai/Mistral-Medium-3.5-128B   mistralai/Mistral-Medium-3.5-128B
Model Size128b
Required VRAM248.5 GB
Updated2026-08-19
MaintainerTheDrummer
Model Typemistral
Model Files  6.0 GB: 0-of-45   5.5 GB: 1-of-45   5.5 GB: 2-of-45   5.5 GB: 3-of-45   5.5 GB: 4-of-45   5.5 GB: 5-of-45   5.5 GB: 6-of-45   5.5 GB: 7-of-45   5.5 GB: 8-of-45   5.5 GB: 9-of-45   5.5 GB: 10-of-45   5.5 GB: 11-of-45   5.5 GB: 12-of-45   5.5 GB: 13-of-45   5.5 GB: 14-of-45   5.5 GB: 15-of-45   5.5 GB: 16-of-45   5.5 GB: 17-of-45   5.5 GB: 18-of-45   5.5 GB: 19-of-45   5.5 GB: 20-of-45   5.5 GB: 21-of-45   5.5 GB: 22-of-45   5.5 GB: 23-of-45   5.5 GB: 24-of-45   5.5 GB: 25-of-45   5.5 GB: 26-of-45   5.5 GB: 27-of-45   5.5 GB: 28-of-45   5.5 GB: 29-of-45   5.5 GB: 30-of-45   5.5 GB: 31-of-45   5.5 GB: 32-of-45   5.5 GB: 33-of-45   5.5 GB: 34-of-45   5.5 GB: 35-of-45   5.5 GB: 36-of-45   5.5 GB: 37-of-45   5.5 GB: 38-of-45   5.5 GB: 39-of-45   5.5 GB: 40-of-45   5.5 GB: 41-of-45   5.5 GB: 42-of-45   5.5 GB: 43-of-45   6.0 GB: 44-of-45
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.5.0
Vocabulary Size131072

Best Alternatives to Behemoth 128B V3

Best Alternatives
Context / RAM
Downloads
Likes
...alComputing.Config.LARGE.XPRT2256K / 250 GB1114