What are the hardware requirements for Mixtral 8x7B Instruct V0.1 FP8?

Mixtral 8x7B Instruct V0.1 FP8 requires approximately 47.1 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 FP8 and how large is it?

Mixtral 8x7B Instruct V0.1 FP8 is developed by neuralmagic, 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.

Where can I download or evaluate Mixtral 8x7B Instruct V0.1 FP8?

Mixtral 8x7B Instruct V0.1 FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mixtral 8x7B Instruct V0.1 FP8 by neuralmagic — VRAM 47.1GB, 32K context

Name: Mixtral 8x7B Instruct V0.1 FP8
Author: neuralmagic

Mixtral 8x7B Instruct V0.1 FP8 is an open-source language model by neuralmagic. Features: 46.7b LLM, VRAM: 47.1GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.17.

Compressed-tensors En Fp8 Instruct Mixtral Moe Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8

Mixtral 8x7B Instruct V0.1 FP8 Parameters and Internals

Model Type

text generation, assistant-like chat

Use Cases

Areas:

commercial, research

Applications:

assistant-like chat

Primary Use Cases:

assistant-like chat, text generation

Limitations:

Not for use in languages other than English, Not for illegal purposes

Additional Notes

Quantization reduces GPU memory requirements by approximately 50%

Supported Languages

English (primary)

Training Details

Data Sources:

ultrachat

Methodology:

Quantization with AutoFP8

Context Length:

4096

Model Architecture:

Mixtral-8x7B-Instruct-v0.1

Input Output

Input Format:

Text input expected in chat-like prompts

Accepted Modalities:

Text

Output Format:

Text

Performance Tips:

Use vLLM backend for efficient deployment

Release Notes

Version:

1.0

Date:

6/8/2024

Notes:

Released with FP8 quantization for efficient inference and reduced resources.

LLM Name	Mixtral 8x7B Instruct V0.1 FP8
Repository 🤗	https://huggingface.co/neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8
Model Size	46.7b
Required VRAM	47.1 GB
Updated	2025-04-08
Maintainer	neuralmagic
Model Type	mixtral
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-10 5.0 GB: 2-of-10 5.0 GB: 3-of-10 5.0 GB: 4-of-10 5.0 GB: 5-of-10 5.0 GB: 6-of-10 5.0 GB: 7-of-10 5.0 GB: 8-of-10 5.0 GB: 9-of-10 2.1 GB: 10-of-10
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Mixtral 8x7B Instruct V0.1 FP8 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 Mixtral 8x7B Instruct V0.1 FP8

Best Alternatives	Context / RAM	Downloads	Likes
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	842893	4720
Mixtral 8x7B Instruct V0.1	32K / 93.6 GB	7	0
Mixtral 8x7B Instruct V0.1 FP8	32K / 47.1 GB	3383	0
Merge Mixtral Prometheus 8x7B	32K / 91.9 GB	12	2
...xtral 8x7B Yes Instruct LimaRP	32K / 93.5 GB	5	1
Notux 8x7b V1	32K / 93.6 GB	43	165
BagelMIsteryTour V2 8x7B	32K / 93.5 GB	94	17
...rkrautLM Mixtral 8x7B Instruct	32K / 93.6 GB	84	22
Sage Ft Mixtral 8x7b	32K / 90 GB	45	25
Dolphin 2.5 Mixtral 8x7b	32K / 93.6 GB	4125	1235

Note: green Score (e.g. "73.2") means that the model is better than neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8.