What are the hardware requirements for Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2?

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 requires approximately 6.6 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 Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 and how large is it?

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 is developed by Zoyd, 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 Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2?

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 by Zoyd — VRAM 6.6GB, 32K context

Name: Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2
Author: Zoyd

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 is an open-source language model by Zoyd. Features: 22b LLM, VRAM: 6.6GB, Context: 32K, License: MNPL-0.1, Quantized, LLM Explorer Score: 0.13.

Code Exl2 Mistral Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Zoyd/bullerwins_Codestral-22B-v0.1-hf-2_2bpw_exl2

Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 Parameters and Internals

Model Type

code generation, fill-in-the-middle

Use Cases

Primary Use Cases:

Code snippet generation, Code documentation, Code explanation, Factorization, Software development aids

Limitations:

No moderation mechanisms present

Additional Notes

Codestral-22B-v0.1 is an advanced code generation model supporting multiple languages and programming-related tasks.

Training Details

Data Sources:

80+ programming languages including Python, Java, C, C++, JavaScript, Bash

Input Output

Accepted Modalities:

code

LLM Name	Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2
Repository 🤗	https://huggingface.co/Zoyd/bullerwins_Codestral-22B-v0.1-hf-2_2bpw_exl2
Model Size	22b
Required VRAM	6.6 GB
Updated	2026-07-12
Maintainer	Zoyd
Model Type	mistral
Model Files	6.6 GB
Supported Languages	code
Quantization Type	exl2
Model Architecture	MistralForCausalLM
License	MNPL-0.1
Context Length	32768
Model Max Length	32768
Transformers Version	4.40.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2 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 Bullerwins Codestral 22B V0.1 Hf 2 2bpw EXL2

Best Alternatives	Context / RAM	Downloads	Likes
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
Codestral 22B V0.1 EXL2 8.0bpw	32K / 20.9 GB	9	3
Codestral 22B V0.1 EXL2 6.0bpw	32K / 16.9 GB	7	1
Codestral 22B V0.1 EXL2 5.0bpw	32K / 14.2 GB	1	1
MS Schisandra 22B V0.2	128K / 44.7 GB	8	9
...ntheon RP Pure 1.6.2 22B Small	128K / 44.7 GB	17	35

Note: green Score (e.g. "73.2") means that the model is better than Zoyd/bullerwins_Codestral-22B-v0.1-hf-2_2bpw_exl2.