What are the hardware requirements for Qwen1.5 0.5B Chat Llamafy?

Qwen1.5 0.5B Chat Llamafy requires approximately 1.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen1.5 0.5B Chat Llamafy and how large is it?

Qwen1.5 0.5B Chat Llamafy is developed by Minami-su, 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.

How does Qwen1.5 0.5B Chat Llamafy perform on standard benchmarks?

Qwen1.5 0.5B Chat Llamafy has the following published scores: MMLU 33.82. Compare against reference models on this page or on the LLM Explorer leaderboards.

Qwen1.5 0.5B Chat Llamafy by Minami-su — VRAM 1.2GB, 4K context

Name: Qwen1.5 0.5B Chat Llamafy
Author: Minami-su

Qwen1.5 0.5B Chat Llamafy is an open-source language model by Minami-su. Features: 0.5b LLM, VRAM: 1.2GB, Context: 4K, License: other, LLM Explorer Score: 0.16, Arc: 30.6, HellaSwag: 44.1, MMLU: 33.8, GSM8K: 7.4.

Conversational En Llama Pytorch Qwen Qwen1.5 Qwen2 Region:us Zh

Model Card on HF 🤗: https://huggingface.co/Minami-su/Qwen1.5-0.5B-Chat_llamafy

Qwen1.5 0.5B Chat Llamafy Parameters and Internals

Model Type

text-generation

Additional Notes

This is a modified version of Qwen1.5 adapted for LLaMA usage, compatible with Transformers library, utilizing a specific conversion script for enhanced capability.

Supported Languages

primary (en), secondary (zh)

Input Output

Accepted Modalities:

text

LLM Name	Qwen1.5 0.5B Chat Llamafy
Repository 🤗	https://huggingface.co/Minami-su/Qwen1.5-0.5B-Chat_llamafy
Model Size	0.5b
Required VRAM	1.2 GB
Updated	2026-07-08
Maintainer	Minami-su
Model Type	llama
Model Files	1.2 GB
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.37.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen1.5 0.5B Chat Llamafy 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 Qwen1.5 0.5B Chat Llamafy

Best Alternatives	Context / RAM	Downloads	Likes
Turn Detector	8K / 0.5 GB	694536	123
CAT Translate 0.8B	8K / 1.6 GB	570	4
...arashina2.2 0.5B Instruct V0.1	8K / 1.6 GB	14012	15
...CLOVAX SEED Text Instruct 0.5B	8K / 1.1 GB	4195	85
Sarashina2.2 0.5B	8K / 1.6 GB	2049	16
Qwen2 0.5B Instruct Llamafy	4K / 1 GB	10	0
Npc Nano 0.5B Base	2K / 1 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than Minami-su/Qwen1.5-0.5B-Chat_llamafy.