What are the hardware requirements for Mixtral 8x7B Instruct V0.1?

Mixtral 8x7B Instruct V0.1 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 Mixtral 8x7B Instruct V0.1 and how large is it?

Mixtral 8x7B Instruct V0.1 is developed by mistralai, 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 Mixtral 8x7B Instruct V0.1 perform on standard benchmarks?

Mixtral 8x7B Instruct V0.1 has the following published scores: MMLU 68.7, LMSYS ELO 1196. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mixtral 8x7B Instruct V0.1 by mistralai — VRAM 93.6GB, 32K context

Name: Mixtral 8x7B Instruct V0.1
Author: mistralai

Mixtral 8x7B Instruct V0.1 is an open-source language model by mistralai. Features: 46.7b LLM, VRAM: 93.6GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, HF Score: 72.6, LLM Explorer Score: 0.47, ELO: 1196, Arc: 90.3, HellaSwag: 80.3, MMLU: 68.7, TruthfulQA: 64.6, WinoGrande: 81.4, GSM8K: 71.7.

Base model:finetune:mistralai/... Base model:mistralai/mixtral-8... De En Es Fr Instruct It Mixtral Moe Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1

Mixtral 8x7B Instruct V0.1 Benchmarks

LMSys ELO: 1196 vs 1272 (so35)^-6%

IFEval: 55.99 vs 88 (so35)^-36.4%

ARC: 90.3 vs 96.7 (so35)^-6.6%

HellaSwag: 80.3 vs 95.3 (gpt4)^-15.7%

MMLU: 68.7 vs 88.3 (so35)^-22.2%

TruthfulQA: 64.58 vs 59 (gpt4)^9.5%

WinoGrande: 81.37 vs 87.5 (gpt4)^-7%

GSM8K: 71.7 vs 96.4 (so35)^-25.6%

OpenCompas: 56.8 vs 73.3 (gpt4)^-22.5%

Exam: 71.4 vs 77.2 (gpt4)^-7.5%

Language: 35.5 vs 62 (gpt4)^-42.7%

Knowledge: 58.8 vs 73.5 (gpt4)^-20%

Understand: 66.7 vs 70 (gpt4)^-4.7%

Reasoning: 54.7 vs 74.4 (gpt4)^-26.5%

MATH Lvl 5: 9.14

LLME Score: 0.47145

^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 8x7B Instruct V0.1 (mistralai/Mixtral-8x7B-Instruct-v0.1)

🌟 Advertise your project 🚀

Mixtral 8x7B Instruct V0.1 Parameters and Internals

Model Type

pretrained generative Sparse Mixture of Experts

Additional Notes

The Mixtral-8x7B Instruct model can be easily fine-tuned and does not have any moderation mechanisms.

Supported Languages

fr (French), it (Italian), de (German), es (Spanish), en (English)

LLM Name	Mixtral 8x7B Instruct V0.1
Repository 🤗	https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
Base Model(s)	mistralai/Mixtral-8x7B-v0.1 mistralai/Mixtral-8x7B-v0.1
Model Size	46.7b
Required VRAM	93.6 GB
Updated	2026-04-22
Maintainer	mistralai
Model Type	mixtral
Instruction-Based	Yes
Model Files	12.1 GB 12.1 GB 12.1 GB 12.1 GB 12.1 GB 12.1 GB 12.1 GB 12.1 GB 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
Supported Languages	fr it de es en
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the Mixtral 8x7B Instruct V0.1

Model	Likes	Downloads	VRAM
...ixtral 8x7B Instruct V0.1 GGUF	655	20684	15 GB
Mixtral 8x7B Instruct V0.1 AWQ	58	11814	24 GB
...ixtral 8x7B Instruct V0.1 GPTQ	141	1452	23 GB
...ixtral 8x7B Instruct V0.1 GGUF	2	358	17 GB
...ixtral 8x7B Instruct V0.1 GGUF	5	281	17 GB
Notux 8x7b V1.3.5bpw EXL2	2	8	20 GB
Notux 8x7b V1.3.5bpw H6 EXL2	1	5	20 GB
...es Mixtral 8x7B 6.0bpw H6 EXL2	1	8	35 GB
...es Mixtral 8x7B 3.0bpw H6 EXL2	1	6	17 GB
...es Mixtral 8x7B 2.4bpw H6 EXL2	2	2	14 GB

Best Alternatives to Mixtral 8x7B Instruct V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 8x7B Instruct V0.1 FP8	32K / 47.1 GB	4845	0
...xtral 8x7B Yes Instruct LimaRP	32K / 93.5 GB	13	1
Merge Mixtral Prometheus 8x7B	32K / 91.9 GB	74	2
...rkrautLM Mixtral 8x7B Instruct	32K / 93.6 GB	539	22
Notux 8x7b V1	32K / 93.6 GB	86	164
BagelMIsteryTour V2 8x7B	32K / 93.5 GB	76	17
Mixtral 8x7B Instruct V0.1 FP8	32K / 47.1 GB	374	0
Sage Ft Mixtral 8x7b	32K / 90 GB	91	24
Dolphin 2.5 Mixtral 8x7b	32K / 93.6 GB	4125	1235
GritLM 8x7B	32K / 93.6 GB	7985	38

Rank the Mixtral 8x7B Instruct V0.1 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? 53232 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 8x7B Instruct V0.1 by mistralai