What are the hardware requirements for Everyone Coder 33B V2 Base 8.0bpw H8 EXL2?

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 requires approximately 33.5 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 and how large is it?

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 is developed by LoneStriker, a model with 33b 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 Everyone Coder 33B V2 Base 8.0bpw H8 EXL2?

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 by LoneStriker — VRAM 33.5GB, 16K context

Name: Everyone Coder 33B V2 Base 8.0bpw H8 EXL2
Author: LoneStriker

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 is an open-source language model by LoneStriker. Features: 33b LLM, VRAM: 33.5GB, Context: 16K, License: other, Quantized, Code Generating, LLM Explorer Score: 0.11.

Codegen Endpoints compatible Exl2 Llama Merge Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 Parameters and Internals

Model Type

coding-specific

Additional Notes

This Version 2 of the Everything-Coder-33b model uses the task_arithmetic merging method which significantly enhances coding performance. It addresses previous merging issues while maintaining model integrity.

Training Details

Data Sources:

deepseek-ai/deepseek-coder-33b-instruct, codefuse-ai/CodeFuse-DeepSeek-33B, WizardLM/WizardCoder-33B-V1.1

Methodology:

fine-tuning and task_arithmetic merging

Input Output

Input Format:

Alpaca prompt format

LLM Name	Everyone Coder 33B V2 Base 8.0bpw H8 EXL2
Repository 🤗	https://huggingface.co/LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2
Model Size	33b
Required VRAM	33.5 GB
Updated	2026-07-14
Maintainer	LoneStriker
Model Type	llama
Model Files	8.6 GB: 1-of-4 8.5 GB: 2-of-4 8.5 GB: 3-of-4 7.9 GB: 4-of-4
Quantization Type	exl2
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizerFast
Beginning of Sentence Token	<｜begin▁of▁sentence｜>
End of Sentence Token	<｜end▁of▁sentence｜>
Vocabulary Size	32256
Torch Data Type	float16

Rank the Everyone Coder 33B V2 Base 8.0bpw H8 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 Everyone Coder 33B V2 Base 8.0bpw H8 EXL2

Best Alternatives	Context / RAM	Downloads	Likes
...erpreter DS 33B 4.0bpw H6 EXL2	16K / 17.1 GB	8	4
...rpreter DS 33B 4.65bpw H6 EXL2	16K / 19.8 GB	5	3
...erpreter DS 33B 5.0bpw H6 EXL2	16K / 21.2 GB	6	1
...erpreter DS 33B 6.0bpw H6 EXL2	16K / 25.3 GB	8	0
...erpreter DS 33B 8.0bpw H8 EXL2	16K / 33.5 GB	5	1
... Coder 33B Base 6.0bpw H6 EXL2	16K / 25.3 GB	3	1
...Coder 33B Base 4.65bpw H6 EXL2	16K / 19.8 GB	1	1
...abbitNeo 33B V1.4.0bpw H6 EXL2	16K / 17.1 GB	5	1
...er 33B Instruct 4.0bpw H6 EXL2	16K / 17.1 GB	5	5
...er 33B Instruct 8.0bpw H8 EXL2	16K / 33.6 GB	6	3

Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2.