What are the hardware requirements for Soar Mistral 123B?

Soar Mistral 123B requires approximately 217.2 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 Soar Mistral 123B and how large is it?

Soar Mistral 123B is developed by julien31, 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 Soar Mistral 123B?

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

Soar Mistral 123B by julien31 — VRAM 217.2GB, 128K context

Name: Soar Mistral 123B
Author: julien31

Soar Mistral 123B is an open-source language model by julien31. Features: 123b LLM, VRAM: 217.2GB, Context: 128K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.19.

Arxiv:2507.14172 4bit Arc Arc-agi Base model:finetune:mistralai/... Base model:mistralai/mistral-l... Code-generation Codegen Conversational Dataset:julien31/soar arc trai... Endpoints compatible Evolutionary-algorithms Instruct Mistral Quantized Region:us Safetensors Sharded Soar Tensorflow

Model Card on HF 🤗: https://huggingface.co/julien31/Soar-mistral-123b

Soar Mistral 123B Parameters and Internals

LLM Name	Soar Mistral 123B
Repository 🤗	https://huggingface.co/julien31/Soar-mistral-123b
Base Model(s)	Mistral Large Instruct 2407 mistralai/Mistral-Large-Instruct-2407
Model Size	123b
Required VRAM	217.2 GB
Updated	2026-07-25
Maintainer	julien31
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
Quantization Type	4bit
Model Architecture	MistralForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.49.0
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Soar Mistral 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 Soar Mistral 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 V4 123B	128K / 222 GB	22	33
Magnum V2 123B	128K / 207.6 GB	62	64

Note: green Score (e.g. "73.2") means that the model is better than julien31/Soar-mistral-123b.