What are the hardware requirements for Mixtral 7Bx2 MoE?

Mixtral 7Bx2 MoE requires approximately 25.8 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 Mixtral 7Bx2 MoE and how large is it?

Mixtral 7Bx2 MoE is developed by cloudyu, a model with 12.9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mixtral 7Bx2 MoE perform on standard benchmarks?

Mixtral 7Bx2 MoE has the following published scores: MMLU 64.98. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mixtral 7Bx2 MoE by cloudyu — VRAM 25.8GB, 32K context

Name: Mixtral 7Bx2 MoE
Rating: 3.5 (2 reviews)
Author: cloudyu

Mixtral 7Bx2 MoE is an open-source language model by cloudyu. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, License: cc-by-nc-4.0, MoE, LLM Explorer Score: 0.18, Arc: 71.3, HellaSwag: 87.5, MMLU: 65, GSM8K: 68.5.

Endpoints compatible Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/cloudyu/Mixtral_7Bx2_MoE

Mixtral 7Bx2 MoE Benchmarks

ARC: 71.25 vs 96.7 (so35)^-26.3%

HellaSwag: 87.45 vs 95.3 (gpt4)^-8.2%

MMLU: 64.98 vs 88.3 (so35)^-26.4%

GSM8K: 68.46 vs 96.4 (so35)^-29%

LLME Score: 0.1798

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Mixtral 7Bx2 MoE (cloudyu/Mixtral_7Bx2_MoE)

🌟 Advertise your project 🚀

Mixtral 7Bx2 MoE Parameters and Internals

Model Type

text-generation

Input Output

Accepted Modalities:

text

Output Format:

text

LLM Name	Mixtral 7Bx2 MoE
Repository 🤗	https://huggingface.co/cloudyu/Mixtral_7Bx2_MoE
Model Size	12.9b
Required VRAM	25.8 GB
Updated	2026-05-22
Maintainer	cloudyu
Model Type	mixtral
Model Files	9.9 GB: 1-of-3 10.0 GB: 2-of-3 5.9 GB: 3-of-3
Model Architecture	MixtralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Mixtral 7Bx2 MoE

Model	Likes	Downloads	VRAM
Mixtral 7Bx2 MoE GGUF	3	217	4 GB
Mixtral 7Bx2 MoE GGUF	24	930	4 GB
Mixtral 7Bx2 MoE GPTQ	8	10	7 GB
Mixtral 7Bx2 MoE AWQ	2	10	7 GB

Best Alternatives to Mixtral 7Bx2 MoE

Best Alternatives	Context / RAM	Downloads	Likes
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	19867	55
Inf Silent Kunoichi V0.1 2x7B	32K / 25.6 GB	6	0
Inf Silent Kunoichi V0.2 2x7B	32K / 25.6 GB	10	1
MixTAO 7Bx2 MoE V8.1	32K / 25.8 GB	8760	52
LogoS 7Bx2 MoE 13B V0.2	32K / 25.9 GB	8281	10
MultiMash8 13B Slerp	32K / 25.7 GB	5	0
MultiMash11 13B Slerp	32K / 25.7 GB	9	0
MultiMash9 13B Slerp	32K / 25.7 GB	5	0
MultiMash10 13B Slerp	32K / 25.7 GB	8	0
Multimash3 12B Slerp	32K / 25.7 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than cloudyu/Mixtral_7Bx2_MoE.

Rank the Mixtral 7Bx2 MoE Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Mixtral 7Bx2 MoE by cloudyu