What are the hardware requirements for Supra2 Medium Base?

Supra2 Medium Base requires approximately 0.1 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Supra2 Medium Base and how large is it?

Supra2 Medium Base is developed by SupraLabs, a model with 25.4m 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 Supra2 Medium Base?

Supra2 Medium Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Supra2 Medium Base by SupraLabs — VRAM 0.1GB, 1K context

Name: Supra2 Medium Base
Author: SupraLabs

Supra2 Medium Base is an open-source language model by SupraLabs. Features: 25.4m LLM, VRAM: 0.1GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.28.

Dataset:huggingfacefw/fineweb-... Efficient En Endpoints compatible Qwen3 Region:us Safetensors Small Supra Supra2 Tiny

Model Card on HF 🤗: https://huggingface.co/SupraLabs/Supra2-Medium-Base

Supra2 Medium Base Parameters and Internals

LLM Name	Supra2 Medium Base
Repository 🤗	https://huggingface.co/SupraLabs/Supra2-Medium-Base
Model Size	25.4m
Required VRAM	0.1 GB
Updated	2026-08-22
Maintainer	SupraLabs
Model Type	qwen3
Model Files	0.1 GB
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	5.5.0
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Vocabulary Size	16384

Rank the Supra2 Medium Base 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 Supra2 Medium Base

Best Alternatives	Context / RAM	Downloads	Likes
Chaturanga Nano	1K / 0.1 GB	405	1
Supra2 Medium Instruct	1K / 0.1 GB	1039	12

Note: green Score (e.g. "73.2") means that the model is better than SupraLabs/Supra2-Medium-Base.