What are the hardware requirements for Magicoder DS 6.7B?

Magicoder DS 6.7B requires approximately 27.1 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 Magicoder DS 6.7B and how large is it?

Magicoder DS 6.7B is developed by ise-uiuc, a model with 6.7b 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 Magicoder DS 6.7B?

Magicoder DS 6.7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Magicoder DS 6.7B by ise-uiuc — VRAM 27.1GB, 16K context

Name: Magicoder DS 6.7B
Author: ise-uiuc

Magicoder DS 6.7B is an open-source language model by ise-uiuc. Features: 6.7b LLM, VRAM: 27.1GB, Context: 16K, License: other, Instruction-Based, LLM Explorer Score: 0.1.

Arxiv:2305.06161 Arxiv:2312.02120 Conversational Dataset:ise-uiuc/magicoder-oss... Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/ise-uiuc/Magicoder-DS-6.7B

Magicoder DS 6.7B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

coding tasks

Limitations:

non-coding tasks

Considerations:

Users should be aware of the risks, biases, and limitations of the model.

Additional Notes

Magicoder models are trained on synthetic data generated by OpenAI models.

Training Details

Data Sources:

Magicoder-OSS-Instruct-75K

Methodology:

OSS-Instruct

Input Output

Accepted Modalities:

text

Performance Tips:

Ensure compliance with OpenAI's terms of use.

LLM Name	Magicoder DS 6.7B
Repository 🤗	https://huggingface.co/ise-uiuc/Magicoder-DS-6.7B
Model Size	6.7b
Required VRAM	27.1 GB
Updated	2026-08-02
Maintainer	ise-uiuc
Model Type	llama
Instruction-Based	Yes
Model Files	4.8 GB: 1-of-6 4.9 GB: 2-of-6 4.9 GB: 3-of-6 4.9 GB: 4-of-6 4.9 GB: 5-of-6 2.7 GB: 6-of-6
Model Architecture	LlamaForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	32256
Torch Data Type	float32

Rank the Magicoder DS 6.7B 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 Magicoder DS 6.7B

Best Alternatives	Context / RAM	Downloads	Likes
Speechless Coder Ds 6.7B	16K / 13.5 GB	459	7
...s Coder6.7b Reflct Adamw Iter1	16K / 13.5 GB	475	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	95	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	110	0
...r6.7b Pos Reflct Rmsprop Iter1	16K / 13.5 GB	87	0
...ir4 Ds Coder6.7b Rmsprop Iter1	16K / 13.5 GB	43	0
Code 290K 6.7B Instruct	16K / 13.5 GB	87	6
...r6.7b Pos Reflct Rmsprop Iter1	16K / 13.5 GB	90	0
...Coder6.7b Reflct Rmsprop Iter1	16K / 13.5 GB	62	0
Ds Coder6.7b Rmsprop Iter1	16K / 13.5 GB	67	0

Note: green Score (e.g. "73.2") means that the model is better than ise-uiuc/Magicoder-DS-6.7B.