What are the hardware requirements for Mixtralmerge 8x7B Rebalanced Test?

Mixtralmerge 8x7B Rebalanced Test requires approximately 93.6 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mixtralmerge 8x7B Rebalanced Test and how large is it?

Mixtralmerge 8x7B Rebalanced Test is developed by chargoddard, a model with 46.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mixtralmerge 8x7B Rebalanced Test perform on standard benchmarks?

Mixtralmerge 8x7B Rebalanced Test has the following published scores: MMLU 70.47. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mixtralmerge 8x7B Rebalanced Test by chargoddard — VRAM 93.6GB, 32K context

Name: Mixtralmerge 8x7B Rebalanced Test
Author: chargoddard

Mixtralmerge 8x7B Rebalanced Test is an open-source language model by chargoddard. Features: 46.7b LLM, VRAM: 93.6GB, Context: 32K, License: cc-by-nc-4.0, MoE, LLM Explorer Score: 0.12, Arc: 68.2, HellaSwag: 85.8, MMLU: 70.5, GSM8K: 58.2.

Conversational Dataset:open-orca/slimorca Endpoints compatible Merge Mergekit Mixtral Moe Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/chargoddard/mixtralmerge-8x7B-rebalanced-test

Mixtralmerge 8x7B Rebalanced Test Parameters and Internals

Additional Notes

This is a dumb experiment with models merged using the Mixtral approach. The effectiveness of the approach is still uncertain.

Training Details

Data Sources:

Open-Orca/SlimOrca

Data Volume:

about ten million tokens

Methodology:

Tuned only the routing parameters

Input Output

Input Format:

ChatML format

LLM Name	Mixtralmerge 8x7B Rebalanced Test
Repository 🤗	https://huggingface.co/chargoddard/mixtralmerge-8x7B-rebalanced-test
Model Size	46.7b
Required VRAM	93.6 GB
Updated	2026-07-24
Maintainer	chargoddard
Model Type	mixtral
Model Files	4.9 GB: 1-of-19 5.0 GB: 2-of-19 5.0 GB: 3-of-19 4.9 GB: 4-of-19 5.0 GB: 5-of-19 5.0 GB: 6-of-19 4.9 GB: 7-of-19 5.0 GB: 8-of-19 5.0 GB: 9-of-19 4.9 GB: 10-of-19 5.0 GB: 11-of-19 5.0 GB: 12-of-19 5.0 GB: 13-of-19 4.9 GB: 14-of-19 5.0 GB: 15-of-19 5.0 GB: 16-of-19 4.9 GB: 17-of-19 5.0 GB: 18-of-19 4.2 GB: 19-of-19 4.9 GB: 1-of-19 5.0 GB: 2-of-19 5.0 GB: 3-of-19 4.9 GB: 4-of-19 5.0 GB: 5-of-19 5.0 GB: 6-of-19 4.9 GB: 7-of-19 5.0 GB: 8-of-19 5.0 GB: 9-of-19 4.9 GB: 10-of-19 5.0 GB: 11-of-19 5.0 GB: 12-of-19 5.0 GB: 13-of-19 4.9 GB: 14-of-19 5.0 GB: 15-of-19 5.0 GB: 16-of-19 4.9 GB: 17-of-19 5.0 GB: 18-of-19 4.2 GB: 19-of-19
Model Architecture	MixtralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32032
Torch Data Type	bfloat16

Rank the Mixtralmerge 8x7B Rebalanced Test 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 Mixtralmerge 8x7B Rebalanced Test

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	842893	4720
Nous Hermes 2 Mixtral 8x7B DPO	32K / 93.6 GB	40865	457
Mixtral 8x7B V0.1	32K / 93.6 GB	49231	1820
Sensualize Mixtral Bf16	32K / 93.6 GB	0	0
Skadi Mixtral V1	32K / 93.5 GB	0	0
Franziska Mixtral V1	32K / 93.5 GB	0	0
Typhon Mixtral V1	32K / 93.4 GB	0	0
GritLM 8x7B KTO	32K / 93.6 GB	7976	3
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	7	0
Smaug Mixtral V0.1	32K / 187.7 GB	8437	12

Note: green Score (e.g. "73.2") means that the model is better than chargoddard/mixtralmerge-8x7B-rebalanced-test.