What are the hardware requirements for Mistral 22B V0.2 AWQ?

Mistral 22B V0.2 AWQ requires approximately 12.2 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 Mistral 22B V0.2 AWQ and how large is it?

Mistral 22B V0.2 AWQ is developed by solidrust, a model with 22b 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 Mistral 22B V0.2 AWQ?

Mistral 22B V0.2 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral 22B V0.2 AWQ by solidrust — VRAM 12.2GB, 64K context

Name: Mistral 22B V0.2 AWQ
Author: solidrust

Mistral 22B V0.2 AWQ is an open-source language model by solidrust. Features: 22b LLM, VRAM: 12.2GB, Context: 64K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

4-bit Autotrain compatible Awq Base model:quantized:vezora/mi... Base model:vezora/mistral-22b-... En Endpoints compatible Mistral Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/solidrust/Mistral-22B-v0.2-AWQ

Mistral 22B V0.2 AWQ Parameters and Internals

Model Type

mistral

Additional Notes

This model is the first working MOE to Dense model conversion. Trained on 8x more data than v0.1.

Supported Languages

en (English)

Input Output

Input Format:

Guanaco prompt format

LLM Name	Mistral 22B V0.2 AWQ
Repository 🤗	https://huggingface.co/solidrust/Mistral-22B-v0.2-AWQ
Model Name	Mistral-22B-v0.2
Model Creator	Vezora
Base Model(s)	Vezora/Mistral-22B-v0.2 Vezora/Mistral-22B-v0.2
Model Size	22b
Required VRAM	12.2 GB
Updated	2026-08-06
Maintainer	solidrust
Model Type	mistral
Model Files	5.0 GB: 1-of-3 5.0 GB: 2-of-3 2.2 GB: 3-of-3
Supported Languages	en
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	65536
Model Max Length	65536
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	float16

Rank the Mistral 22B V0.2 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 Mistral 22B V0.2 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 22B V0.1 AWQ	64K / 12.2 GB	2	1
Codestral 22B V0.1 AWQ	32K / 12.2 GB	6876	0
Codestral 22B V0.1 Hf AWQ	32K / 12.2 GB	402	2
Codestral 22B V0.1 AWQ	32K / 12.2 GB	113	0
Codestral 22B V0.1 Hf AWQ	32K / 12.2 GB	7	0
MwM 22B Instruct	128K / 44.7 GB	6	0
... Instruct 0.2 Chkpt 200 16 Bit	128K / 44.7 GB	6	1
...l 22B V0.1 Hf FIM Fix Bnb 4bit	32K / 13.1 GB	1	1
Text2cypher Codestral 16bit	32K / 44.7 GB	7	3
... Abliterated V3.8.0bpw H8 EXL2	32K / 21.2 GB	2	1

Note: green Score (e.g. "73.2") means that the model is better than solidrust/Mistral-22B-v0.2-AWQ.