What are the hardware requirements for Mixtral 8x22B V0.1 AWQ?

Mixtral 8x22B V0.1 AWQ requires approximately 73.7 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mixtral 8x22B V0.1 AWQ and how large is it?

Mixtral 8x22B V0.1 AWQ is developed by mistral-community, a model with 140.6b 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 8x22B V0.1 AWQ?

Mixtral 8x22B V0.1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mixtral 8x22B V0.1 AWQ by mistral-community — VRAM 73.7GB, 64K context

Name: Mixtral 8x22B V0.1 AWQ
Author: mistral-community

Mixtral 8x22B V0.1 AWQ is an open-source language model by mistral-community. Features: 140.6b LLM, VRAM: 73.7GB, Context: 64K, MoE, Quantized, LLM Explorer Score: 0.12.

4-bit Autotrain compatible Awq Base model:quantized:v2ray/mix... Base model:v2ray/mixtral-8x22b... De Deploy:azure En Endpoints compatible Es Fr It Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1-AWQ

Mixtral 8x22B V0.1 AWQ Parameters and Internals

Model Type

text-generation, quantized

Additional Notes

The model supports inference via quantized (AWQ) format. The quantization was performed by MaziyarPanahi to allow more efficient inference.

Supported Languages

en (high), es (high), de (high), it (high), fr (high)

Training Details

Context Length:

65000

Model Architecture:

176B MoE with ~40B active

Input Output

Accepted Modalities:

text

LLM Name	Mixtral 8x22B V0.1 AWQ
Repository 🤗	https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1-AWQ
Model Name	Mixtral-8x22B-v0.1-AWQ
Model Creator	v2ray
Base Model(s)	v2ray/Mixtral-8x22B-v0.1 v2ray/Mixtral-8x22B-v0.1
Model Size	140.6b
Required VRAM	73.7 GB
Updated	2026-04-20
Maintainer	mistral-community
Model Type	mixtral
Model Files	5.0 GB: 1-of-15 5.0 GB: 2-of-15 5.0 GB: 3-of-15 5.0 GB: 4-of-15 5.0 GB: 5-of-15 5.0 GB: 6-of-15 5.0 GB: 7-of-15 5.0 GB: 8-of-15 5.0 GB: 9-of-15 5.0 GB: 10-of-15 5.0 GB: 11-of-15 5.0 GB: 12-of-15 5.0 GB: 13-of-15 5.0 GB: 14-of-15 3.7 GB: 15-of-15
Supported Languages	en es de it fr
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MixtralForCausalLM
Context Length	65536
Model Max Length	65536
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Mixtral 8x22B V0.1 AWQ 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 8x22B V0.1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
...ixtral 8x22B Instruct V0.1 AWQ	64K / 73.7 GB	6689	13
...olphin 2.9.2 Mixtral 8x22b AWQ	64K / 73.7 GB	51	0
WizardLM 2 8x22B AWQ	64K / 73.7 GB	75	13
Karasu Mixtral 8x22B V0.1 AWQ	64K / 73.7 GB	5	7
Zephyr Orpo 141B A35b V0.1 AWQ	64K / 73.7 GB	4	3
Mixtral 8x22B Instruct V0.1	64K / 221.4 GB	71589	756
Zephyr Orpo 141B A35b V0.1	64K / 207.2 GB	66	270
WizardLM 2 8x22B	64K / 216.8 GB	9656	415
Mixtral 8x22B V0.1	64K / 221.6 GB	5069	239
...ixtral 8x22B Instruct V0.1 FP8	64K / 140.9 GB	11259	0

Note: green Score (e.g. "73.2") means that the model is better than mistral-community/Mixtral-8x22B-v0.1-AWQ.