What are the hardware requirements for Starlight Small 1?

Starlight Small 1 requires approximately 1.5 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Starlight Small 1 and how large is it?

Starlight Small 1 is developed by North-ML1, a model with 0.8b 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 Starlight Small 1?

Starlight Small 1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Starlight Small 1 by North-ML1 — VRAM 1.5GB, 256K context

Name: Starlight Small 1
Author: North-ML1

Starlight Small 1 is an open-source language model by North-ML1. Features: 0.8b LLM, VRAM: 1.5GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.31.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-0.8b Conversational En North-ml Qwen3 5 text Region:us Safetensors Starlight

Model Card on HF 🤗: https://huggingface.co/North-ML1/starlight-small-1

Starlight Small 1 Parameters and Internals

LLM Name	Starlight Small 1
Repository 🤗	https://huggingface.co/North-ML1/starlight-small-1
Base Model(s)	Qwen/Qwen3.5-0.8B Qwen/Qwen3.5-0.8B
Model Size	0.8b
Required VRAM	1.5 GB
Updated	2026-10-10
Maintainer	North-ML1
Model Type	qwen3_5_text
Model Files	0.0 GB 1.5 GB
Supported Languages	en
Model Architecture	Qwen3_5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.17.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Starlight Small 1 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 Starlight Small 1

Best Alternatives	Context / RAM	Downloads	Likes
Jev Decisions V1 Model	256K / 1.5 GB	514	1
PrimeMind 0.8B	256K / 1.5 GB	535	2
Qwen3.5 0.8B Fable GPT6	256K / 1.5 GB	177	0
Qwen 3.5 0.8B Hedgehog	256K / 1.5 GB	438	0
AlphaRoute 0.8B V1.0	256K / 1.5 GB	209	1
Quipu 0.8B	256K / 1.5 GB	118	1
St4 Annealing Sft	256K / 1.5 GB	526	0
St4 Generic Sft	256K / 1.5 GB	386	0
St5 Generic Sft	256K / 1.5 GB	304	0
St3 Response Sft	256K / 1.5 GB	109	0

Note: green Score (e.g. "73.2") means that the model is better than North-ML1/starlight-small-1.