What are the hardware requirements for Andromeda Code 0.5B?

Andromeda Code 0.5B requires approximately 1 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 Andromeda Code 0.5B and how large is it?

Andromeda Code 0.5B is developed by fiel1986, a model with 0.5b 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 Andromeda Code 0.5B?

Andromeda Code 0.5B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Andromeda Code 0.5B by fiel1986 — VRAM 1GB, 32K context

Name: Andromeda Code 0.5B
Author: fiel1986

Andromeda Code 0.5B is an open-source language model by fiel1986. Features: 0.5b LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i... Code Codigo Conversational Deepseek Destilacion Endpoints compatible Es Espanol Instruct Qwen Qwen2 Region:us Response-distillation Safetensors

Model Card on HF 🤗: https://huggingface.co/fiel1986/Andromeda-Code-0.5B

Andromeda Code 0.5B Parameters and Internals

LLM Name	Andromeda Code 0.5B
Repository 🤗	https://huggingface.co/fiel1986/Andromeda-Code-0.5B
Base Model(s)	Qwen/Qwen2.5-0.5B-Instruct Qwen/Qwen2.5-0.5B-Instruct
Model Size	0.5b
Required VRAM	1 GB
Updated	2026-10-13
Maintainer	fiel1986
Model Type	qwen2
Instruction-Based	Yes
Model Files	1.0 GB
Supported Languages	es
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.16.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Andromeda Code 0.5B 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 Andromeda Code 0.5B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2 0.5B Abyme Merge3	128K / 1.3 GB	33	1
Qwen2 0.5B Abyme Merge2	128K / 0.3 GB	27	0
Qwen2.5 0.5B Instruct	64K / 1 GB	16	0
Qwen2.5 0.5B Instruct	32K / 1 GB	6324790	572
Qwen2.5 0.5B Abliterated	32K / 1.3 GB	1450	1
Seger Qwen2.5 0.5B	32K / 1 GB	599	0
Temper 1 0.5B	32K / 1 GB	241	2
Qwen2.5 0.5B Grounded Sft	32K / 1 GB	728	1
Qwen2.5 0.5B Grounded Rloo	32K / 1 GB	705	1
Sawyer 0.5B	32K / 1 GB	474	3

Note: green Score (e.g. "73.2") means that the model is better than fiel1986/Andromeda-Code-0.5B.