What are the hardware requirements for Magnum V4 123B?

Magnum V4 123B requires approximately 222 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 Magnum V4 123B and how large is it?

Magnum V4 123B is developed by anthracite-org, 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 Magnum V4 123B?

Magnum V4 123B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Magnum V4 123B by anthracite-org — VRAM 222GB, 128K context

Name: Magnum V4 123B
Author: anthracite-org

Magnum V4 123B is an open-source language model by anthracite-org. Features: 123b LLM, VRAM: 222GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.15.

Chat Conversational Dataset:anthracite-org/c2 logs... Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:anthracite-org/nopm cl... Dataset:lodrick-the-lafted/kal... En Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/anthracite-org/magnum-v4-123b

Magnum V4 123B Parameters and Internals

LLM Name	Magnum V4 123B
Repository 🤗	https://huggingface.co/anthracite-org/magnum-v4-123b
Model Size	123b
Required VRAM	222 GB
Updated	2026-07-20
Maintainer	anthracite-org
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-51 4.8 GB: 2-of-51 4.9 GB: 3-of-51 4.8 GB: 4-of-51 4.8 GB: 5-of-51 4.8 GB: 6-of-51 4.9 GB: 7-of-51 4.8 GB: 8-of-51 4.8 GB: 9-of-51 4.8 GB: 10-of-51 4.9 GB: 11-of-51 4.8 GB: 12-of-51 4.8 GB: 13-of-51 4.8 GB: 14-of-51 4.9 GB: 15-of-51 4.8 GB: 16-of-51 4.8 GB: 17-of-51 4.8 GB: 18-of-51 4.9 GB: 19-of-51 4.8 GB: 20-of-51 4.8 GB: 21-of-51 4.8 GB: 22-of-51 4.9 GB: 23-of-51 4.8 GB: 24-of-51 4.8 GB: 25-of-51 4.8 GB: 26-of-51 4.9 GB: 27-of-51 4.8 GB: 28-of-51 4.8 GB: 29-of-51 4.8 GB: 30-of-51 4.9 GB: 31-of-51 4.8 GB: 32-of-51 4.8 GB: 33-of-51 4.8 GB: 34-of-51 4.9 GB: 35-of-51 4.8 GB: 36-of-51 4.8 GB: 37-of-51 4.8 GB: 38-of-51 4.9 GB: 39-of-51 4.8 GB: 40-of-51 4.8 GB: 41-of-51 4.8 GB: 42-of-51 4.9 GB: 43-of-51 4.8 GB: 44-of-51 4.8 GB: 45-of-51 4.8 GB: 46-of-51
Supported Languages	en
Model Architecture	MistralForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.45.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Magnum V4 123B 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 Magnum V4 123B

Best Alternatives	Context / RAM	Downloads	Likes
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
Cakrawala 123B	128K / 222 GB	6	4
Behemoth 123B V2	128K / 221.6 GB	4	10
Behemoth 123B V1	128K / 221.6 GB	6	44
Magnum V2 123B	128K / 207.6 GB	62	64
Lumikabra 123B V0.4	128K / 216.7 GB	9	12

Note: green Score (e.g. "73.2") means that the model is better than anthracite-org/magnum-v4-123b.