What are the hardware requirements for Monstral 123B V2?

Monstral 123B V2 requires approximately 245.4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Monstral 123B V2 and how large is it?

Monstral 123B V2 is developed by MarsupialAI, a model with 123b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Monstral 123B V2?

Monstral 123B V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Monstral 123B V2 by MarsupialAI — VRAM 245.4GB, 128K context

Name: Monstral 123B V2
Author: MarsupialAI

Monstral 123B V2 is an open-source language model by MarsupialAI. Features: 123b LLM, VRAM: 245.4GB, Context: 128K, License: other, Merged, LLM Explorer Score: 0.16.

Merged Model Chat Conversational En Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/MarsupialAI/Monstral-123B-v2

Monstral 123B V2 Parameters and Internals

LLM Name	Monstral 123B V2
Repository 🤗	https://huggingface.co/MarsupialAI/Monstral-123B-v2
Merged Model	Yes
Model Size	123b
Required VRAM	245.4 GB
Updated	2026-08-06
Maintainer	MarsupialAI
Model Type	mistral
Model Files	15.5 GB: 1-of-16 16.0 GB: 2-of-16 15.9 GB: 3-of-16 15.9 GB: 4-of-16 15.9 GB: 5-of-16 16.0 GB: 6-of-16 15.9 GB: 7-of-16 15.9 GB: 8-of-16 15.9 GB: 9-of-16 16.0 GB: 10-of-16 15.9 GB: 11-of-16 15.9 GB: 12-of-16 15.9 GB: 13-of-16 16.0 GB: 14-of-16 15.9 GB: 15-of-16 6.9 GB: 16-of-16
Supported Languages	en
Model Architecture	MistralForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.46.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	float16

Rank the Monstral 123B V2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Monstral 123B V2

Best Alternatives	Context / RAM	Downloads	Likes
Behemoth X R1 123B	128K / 216.7 GB	8	2
Behemoth X 123B V2.1	128K / 222 GB	15	7
Behemoth ReduX 123B V1	128K / 217.2 GB	70	14
Behemoth X 123B V2	128K / 217.2 GB	47	32
Behemoth R1 123B V2	128K / 226.4 GB	12	29
ML2 123B Magnum Diamond	128K / 212.4 GB	126	13
Gigaberg Mistral Large 123B	128K / 222 GB	6	2
Behemoth 123B V1.2	128K / 226.4 GB	6	30
Behemoth 123B V2.2	128K / 226.4 GB	7	27
Behemoth V1.2 Magnum V4 123B	128K / 216.7 GB	7	5

Note: green Score (e.g. "73.2") means that the model is better than MarsupialAI/Monstral-123B-v2.