What are the hardware requirements for Codestral 22B V0.1 AWQ?

Codestral 22B V0.1 AWQ requires approximately 12.2 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 Codestral 22B V0.1 AWQ and how large is it?

Codestral 22B V0.1 AWQ is developed by stelterlab, 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 Codestral 22B V0.1 AWQ?

Codestral 22B V0.1 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codestral 22B V0.1 AWQ by stelterlab — VRAM 12.2GB, 32K context

Name: Codestral 22B V0.1 AWQ
Author: stelterlab

Codestral 22B V0.1 AWQ is an open-source language model by stelterlab. Features: 22b LLM, VRAM: 12.2GB, Context: 32K, License: MNPL-0.1, Quantized, LLM Explorer Score: 0.13.

4-bit Awq Code Endpoints compatible Mistral Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/stelterlab/Codestral-22B-v0.1-AWQ

Codestral 22B V0.1 AWQ Parameters and Internals

Model Type

text generation, code understanding

Use Cases

Areas:

software development, education

Applications:

VS Code add-ons

Primary Use Cases:

code generation, code explanation

Limitations:

Lack of moderation mechanisms

Considerations:

Engage with community to implement guardrails.

Additional Notes

Quantized version using AutoAWQ. Supports Fill-in-the-Middle (FIM) requests.

LLM Name	Codestral 22B V0.1 AWQ
Repository 🤗	https://huggingface.co/stelterlab/Codestral-22B-v0.1-AWQ
Base Model(s)	bullerwins/Codestral-22B-v0.1-hf bullerwins/Codestral-22B-v0.1-hf
Model Size	22b
Required VRAM	12.2 GB
Updated	2026-07-23
Maintainer	stelterlab
Model Type	mistral
Model Files	10.0 GB: 1-of-2 2.2 GB: 2-of-2
Supported Languages	code
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	MistralForCausalLM
License	MNPL-0.1
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	float16

Rank the Codestral 22B 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 Codestral 22B V0.1 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 22B V0.2 AWQ	64K / 12.2 GB	9	2
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 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 stelterlab/Codestral-22B-v0.1-AWQ.