Cleanup 1 needs about 2.1 GB of memory at Q8_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Cleanup 1: a small language model that cleans up dictated text on device
Cleanup 1 is a 0.596B parameter model fine‑tuned from Qwen3‑0.6B‑Base. It removes filler words, repeats, and adds punctuation, capitalization, and digits while preserving the speaker’s wording. It runs locally with llama.cpp on Windows and Linux.
Good at
- Cleaning dictated text
- Preserving speaker wording
- Adding punctuation and capitalization
Limits
- No question answering or instruction execution
- Limited to 32768 context tokens
- No vision support
Best for
- Local dictation cleanup
- Speech-to-text post‑processing
- On‑device text formatting
Who it’s for. Developers integrating local cleanup in dictation apps. Users needing offline text refinement without external services.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.6 GB | 2.1 GB | Fits | Get file → |
The Q8_0 quant is 0.64 GB and needs about 2.1 GB VRAM at 8 k context. For 8 GB VRAM, Q8_0 is suitable. If memory is tighter, no other quant is available in the file list.
What GPU do you need for Cleanup 1?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (0.6 GB file, about 2.1 GB in use).
Which Cleanup 1 quant should you choose?
Q8_0 (0.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Cleanup 1
How much VRAM does Cleanup 1 need?
About 2.1 GB at Q8_0 with an 8K context window. That is the 0.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Cleanup 1 on an 8 GB GPU?
Yes, with Q8_0: the 0.6 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Cleanup 1 GGUF?
It depends on the quant: Q8_0 is 0.6 GB.
What context length does Cleanup 1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Cleanup 1 GGUF?
The files are on Hugging Face in the spokenly/cleanup-1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Cleanup 1 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Cleanup 1 on 8 GB VRAM?
Yes, the Q8_0 quant requires about 2.1 GB VRAM at 8 k context, well within an 8 GB budget.
Does Cleanup 1 support other languages?
It works best in English and also supports German, Spanish, French, Chinese, Russian, and Japanese, though quality is lower.