What are the hardware requirements for Cleanup 1?

Cleanup 1 requires approximately 1.2 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 Cleanup 1 and how large is it?

Cleanup 1 is developed by spokenly, a model with 0.6b 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 Cleanup 1?

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

Cleanup 1 by spokenly — VRAM 1.2GB, 32K context

Name: Cleanup 1
Author: spokenly

Cleanup 1 is an open-source language model by spokenly. Features: 0.6b LLM, VRAM: 1.2GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.31.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-0.6b-bas... Conversational De Dictation En Endpoints compatible Es Fr Ja Mlx On-device Post-processing Punctuation Qwen3 Region:us Ru Safetensors Text-cleanup Zh

Model Card on HF 🤗: https://huggingface.co/spokenly/cleanup-1

Cleanup 1 Parameters and Internals

LLM Name	Cleanup 1
Repository 🤗	https://huggingface.co/spokenly/cleanup-1
Base Model(s)	Qwen/Qwen3-0.6B-Base Qwen/Qwen3-0.6B-Base
Model Size	0.6b
Required VRAM	1.2 GB
Updated	2026-10-14
Maintainer	spokenly
Model Type	qwen3
Model Files	1.2 GB
Supported Languages	en de es fr zh ru ja
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Cleanup 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 Cleanup 1

Best Alternatives	Context / RAM	Downloads	Likes
S1 Mini	40K / 1.5 GB	1136	180
Qwen3 Reranker 0.6B	40K / 1.2 GB	2508313	377
E2etext T1edu1 T1	40K / 1.2 GB	995	1
Qwen3 Finetuned	40K / 2.4 GB	178	1
Cultist Simulator Qwen3 0.6B	40K / 1.2 GB	323	0
Qwen3 0.6B FP8	40K / 1.1 GB	1581403	62
Qwen3 0.6B JSON SFT	40K / 1.2 GB	231	0
Qwen3 0.6B JSON SFT	40K / 1.2 GB	231	0
Adtc Agri Sft Qwen3 0.6B	40K / 1.2 GB	619	0
Qwen3 0.6B Heretic	40K / 1.2 GB	238	0

Note: green Score (e.g. "73.2") means that the model is better than spokenly/cleanup-1.