What are the hardware requirements for Basal 1.5 Mini?

Basal 1.5 Mini requires approximately 3.2 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Basal 1.5 Mini and how large is it?

Basal 1.5 Mini is developed by Remek, a model with 1.5b 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 Basal 1.5 Mini?

Basal 1.5 Mini is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Basal 1.5 Mini by Remek — VRAM 3.2GB, 8K context

Name: Basal 1.5 Mini
Author: Remek

Basal 1.5 Mini is an open-source language model by Remek. Features: 1.5b LLM, VRAM: 3.2GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.32.

Base model:finetune:speakleash... Base model:speakleash/bielik-1... Calibration Classification Conversational Decision-making En Endpoints compatible Instruct Llama Pl Polish Region:us Safetensors Typed-decisions

Model Card on HF 🤗: https://huggingface.co/Remek/basal-1.5-mini

Basal 1.5 Mini Parameters and Internals

LLM Name	Basal 1.5 Mini
Repository 🤗	https://huggingface.co/Remek/basal-1.5-mini
Base Model(s)	speakleash/Bielik-1.5B-v3.0-Instruct speakleash/Bielik-1.5B-v3.0-Instruct
Model Size	1.5b
Required VRAM	3.2 GB
Updated	2026-10-08
Maintainer	Remek
Model Type	llama
Instruction-Based	Yes
Model Files	0.0 GB 3.2 GB
Supported Languages	pl en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	5.17.0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000

Rank the Basal 1.5 Mini 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 Basal 1.5 Mini

Best Alternatives	Context / RAM	Downloads	Likes
Meow Clovax V3	128K / 6.3 GB	11	0
Basal 1.0 1.5B	8K / 3.2 GB	903	2
OpenCoder 1.5B Instruct	4K / 3.8 GB	369	49