What are the hardware requirements for Mixtral 8x22b Instruct Oh EXL2 2.25bpw?

Mixtral 8x22b Instruct Oh EXL2 2.25bpw requires approximately 40.1 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 Oh EXL2 2.25bpw and how large is it?

Mixtral 8x22b Instruct Oh EXL2 2.25bpw is developed by Dracones. 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 Oh EXL2 2.25bpw?

Mixtral 8x22b Instruct Oh EXL2 2.25bpw is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mixtral 8x22b Instruct Oh EXL2 2.25bpw by Dracones — VRAM 40.1GB, 64K context

Name: Mixtral 8x22b Instruct Oh EXL2 2.25bpw
Author: Dracones

Mixtral 8x22b Instruct Oh EXL2 2.25bpw is an open-source language model by Dracones. Features: LLM, VRAM: 40.1GB, Context: 64K, License: apache-2.0, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

Base model:mistral-community/m... Base model:quantized:mistral-c... Conversational Dataset:teknium/openhermes-2.5 En Endpoints compatible Exl2 Instruct Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Dracones/mixtral-8x22b-instruct-oh_exl2_2.25bpw

Mixtral 8x22b Instruct Oh EXL2 2.25bpw Parameters and Internals

Model Type

text generation

Additional Notes

These quants were made with exllamav2 version 0.0.18. Quants made on this version of EXL2 may not work on older versions of the exllamav2 library. If you have problems loading these models, please update Text Generation WebUI to the latest version.

LLM Name	Mixtral 8x22b Instruct Oh EXL2 2.25bpw
Repository 🤗	https://huggingface.co/Dracones/mixtral-8x22b-instruct-oh_exl2_2.25bpw
Base Model(s)	mistral-community/Mixtral-8x22B-v0.1 mistral-community/Mixtral-8x22B-v0.1
Required VRAM	40.1 GB
Updated	2026-07-20
Maintainer	Dracones
Model Type	mixtral
Instruction-Based	Yes
Model Files	8.6 GB: 1-of-5 8.6 GB: 2-of-5 8.6 GB: 3-of-5 8.6 GB: 4-of-5 5.7 GB: 5-of-5
Supported Languages	en
Quantization Type	exl2
Model Architecture	MixtralForCausalLM
License	apache-2.0
Context Length	65536
Model Max Length	65536
Transformers Version	4.39.3
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Mixtral 8x22b Instruct Oh EXL2 2.25bpw 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 Oh EXL2 2.25bpw

Best Alternatives	Context / RAM	Downloads	Likes
...M 2 8x22B Beige 5.0bpw H6 EXL2	64K / 88.5 GB	8	0
...M 2 8x22B Beige 4.0bpw H6 EXL2	64K / 70.8 GB	6	0
...M 2 8x22B Beige 2.4bpw H6 EXL2	64K / 42.7 GB	5	0
...M 2 8x22B Beige 3.0bpw H6 EXL2	64K / 53.2 GB	5	0
...B Instruct V0.1 8.0bpw H8 EXL2	64K / 120.2 GB	6	1
...eryTour V2 8x7B 4.5bpw H6 EXL2	32K / 26.5 GB	5	2
...it MoE 2bitgs8 Metaoffload HQQ	32K / 24.1 GB	9	19
...hin 2.7 Mixtral 8x7b 8bpw EXL2	32K / 46.8 GB	5	2
... 4bit MoE 3bit Metaoffload HQQ	32K / 22.4 GB	12	13
... 4bit MoE 2bit Metaoffload HQQ	32K / 18.3 GB	32	16

Note: green Score (e.g. "73.2") means that the model is better than Dracones/mixtral-8x22b-instruct-oh_exl2_2.25bpw.