What are the hardware requirements for Mixtral 8x22B Instruct V0.1 GPTQ 8bit?

Mixtral 8x22B Instruct V0.1 GPTQ 8bit requires approximately 143.8 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 Instruct V0.1 GPTQ 8bit and how large is it?

Mixtral 8x22B Instruct V0.1 GPTQ 8bit is developed by jarrelscy, 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 Instruct V0.1 GPTQ 8bit?

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

Mixtral 8x22B Instruct V0.1 GPTQ 8bit by jarrelscy — VRAM 143.8GB, 64K context

Name: Mixtral 8x22B Instruct V0.1 GPTQ 8bit
Author: jarrelscy

Mixtral 8x22B Instruct V0.1 GPTQ 8bit is an open-source language model by jarrelscy. Features: 140.6b LLM, VRAM: 143.8GB, Context: 64K, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

8-bit 8bit Conversational Endpoints compatible Gptq Instruct Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-8bit

Mixtral 8x22B Instruct V0.1 GPTQ 8bit Parameters and Internals

Model Type

quantized 8-bit

Additional Notes

WIP - do not use currently See original model card for more information.

LLM Name	Mixtral 8x22B Instruct V0.1 GPTQ 8bit
Repository 🤗	https://huggingface.co/jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-8bit
Model Size	140.6b
Required VRAM	143.8 GB
Updated	2026-08-02
Maintainer	jarrelscy
Model Type	mixtral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-30 4.9 GB: 2-of-30 4.9 GB: 3-of-30 4.9 GB: 4-of-30 4.9 GB: 5-of-30 4.9 GB: 6-of-30 4.9 GB: 7-of-30 4.9 GB: 8-of-30 4.9 GB: 9-of-30 4.9 GB: 10-of-30 4.9 GB: 11-of-30 4.9 GB: 12-of-30 4.9 GB: 13-of-30 4.9 GB: 14-of-30 4.9 GB: 15-of-30 4.9 GB: 16-of-30 4.9 GB: 17-of-30 4.9 GB: 18-of-30 4.9 GB: 19-of-30 4.9 GB: 20-of-30 4.9 GB: 21-of-30 4.9 GB: 22-of-30 5.0 GB: 23-of-30 5.0 GB: 24-of-30 4.9 GB: 25-of-30 4.9 GB: 26-of-30 4.9 GB: 27-of-30 4.9 GB: 28-of-30 4.9 GB: 29-of-30 1.5 GB: 30-of-30
GPTQ Quantization	Yes
Quantization Type	gptq\|8bit
Model Architecture	MixtralForCausalLM
Context Length	65536
Model Max Length	65536
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	float16

Rank the Mixtral 8x22B Instruct V0.1 GPTQ 8bit 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 Instruct V0.1 GPTQ 8bit

Best Alternatives	Context / RAM	Downloads	Likes
... 8x22B Instruct V0.1 GPTQ 4bit	64K / 74.1 GB	106	1
Mixtral 8x22B Instruct V0.1	64K / 221.4 GB	71589	756
...ixtral 8x22B Instruct V0.1 FP8	64K / 140.9 GB	11259	0
...ixtral 8x22B Instruct V0.1 AWQ	64K / 73.7 GB	6689	13
...igHuggyD Grey WizardLM 2 8x22B	64K / 216.6 GB	12	4
...x22B Instruct V0.1 FP8 Dynamic	64K / 140.9 GB	22	0
WizardLM 2 8x22B Beige	64K / 221.4 GB	8	4
...ral 8x22B Instruct V0.1 FP8 V2	64K / 140.9 GB	5	0
...ral 8x22B Instruct V0.1 FP8 V1	64K / 140.9 GB	6	0
Mixtral 8x22B GO Instruct V1	64K / 280.8 GB	33	2

Note: green Score (e.g. "73.2") means that the model is better than jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-8bit.