DataLearner logo
MI

Mixtral-8×7B-MoE

Chat modelMixtral-8

Mixtral-8×7B-MoE-Instruct-v0.1

Release date: 2023-12-08Updated: 2024-03-27 21:27:01685
Live demoGitHubHugging FaceCompare
Parameters
45B
Context length
32K
Chinese support
Not supported
Reasoning ability

Mixtral-8×7B-MoE-Instruct-v0.1 is an AI model published by MistralAI, released on 2023-12-08, for Chat model, with 45B parameters, and 32K context length, requiring about 86.99GB storage, with a 74.40 score on GSM8K.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Mixtral-8×7B-MoE

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
32K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
No data
Release date
2023-12-08
Model file size
86.99GB
MoE architecture
No
Total params / Active params
45B / N/A
Knowledge cutoff
No data
Mixtral-8×7B-MoE

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
GitHub link unavailable
Live demo
No live demo
Mixtral-8×7B-MoE

Official resources

Paper
DataLearnerAI blog
Mixtral-8×7B-MoE

API details

API speed
No data
No public API pricing yet.
Mixtral-8×7B-MoE

Benchmark Results

Mixtral-8×7B-MoE currently shows benchmark results led by GSM8K (27 / 70, score 74.40), MBPP (28 / 70, score 60.70), MMLU (72 / 124, score 70.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
70.60
72 / 124

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
74.40
27 / 70

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
60.70
28 / 70
HumanEval
Standard Mode
40.20
61 / 101

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Mixtral-8×7B-MoE

Publisher

Mixtral-8×7B-MoE-Instruct-v0.1

Model Overview

Mixtral-8×7B-MoE-Instruct-v0.1 is an AI model published by MistralAI, released on 2023-12-08, for Chat model, with 45B parameters, and 32K context length, requiring about 86.99GB storage, with a 74.40 score on GSM8K.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code