qwen35 2b muesli cleanup v12 needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.3 GB (Q4_K_M) to 2.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
On‑device dictation cleanup model for macOS Muesli
qwen35 2b muesli cleanup v12 is a GGUF model based on Qwen3.5‑2B. It cleans raw speech‑to‑text output, removes fillers, corrects errors, and formats lists according to the target app’s punctuation style. The model is optimized for on‑device inference with llama.cpp.
Good at
- reasoning
- tools
- dictation cleanup
Limits
- no vision support
- licensed under apache-2.0
- requires 8‑k context for full accuracy
Best for
- macOS dictation apps
- speech‑to‑text post‑processing
- cleaning raw transcripts
Who it’s for. Developers building dictation or transcription tools that need lightweight, on‑device text cleanup. Also useful for researchers prototyping speech‑to‑text pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8‑GB VRAM, use Q4_K_M (1.27 GB file, ~2.2 GB VRAM at 8‑k context). If 16‑GB VRAM is available, Q8_0 (2.01 GB file, ~2.9 GB VRAM) offers higher precision. Memory estimates are approximate.
What GPU do you need for qwen35 2b muesli cleanup v12?
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 (2.0 GB file, about 2.9 GB in use).
Which qwen35 2b muesli cleanup v12 quant should you choose?
Q4_K_M is the usual starting point for qwen35 2b muesli cleanup v12: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwen35 2b muesli cleanup v12
How much VRAM does qwen35 2b muesli cleanup v12 need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 qwen35 2b muesli cleanup v12 on an 8 GB GPU?
Yes, with Q8_0: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qwen35 2b muesli cleanup v12 GGUF?
It depends on the quant: Q4_K_M is 1.3 GB, Q8_0 is 2.0 GB.
What context length does qwen35 2b muesli cleanup v12 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download qwen35 2b muesli cleanup v12 GGUF?
The files are on Hugging Face in the Muesli-HQ/qwen35-2b-muesli-cleanup-v12-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 qwen35 2b muesli cleanup v12 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 2.2 GB VRAM at 8‑k context, fitting within an 8‑GB GPU. The Q8_0 quantization needs about 2.9 GB VRAM and is also feasible on 8 GB GPUs with some headroom.
Does this model support vision?
No, the model is text‑only and has no vision capabilities.
What license does it use?
The model is released under the apache-2.0 license, allowing free use and modification.