.QwenCleo-ASR-gguf-root needs about 3.3 GB of memory at Q8_0 (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.5 GB (Q8_0) to 4.1 GB (F16).
QwenCleo-ASR: Egyptian Arabic and code‑switching speech recognition
QwenCleo-ASR is a fine‑tuned Qwen3‑ASR‑1.7B model for Egyptian Arabic and Arabic↔English code‑switching. It achieves 19.85% WER on a 3,699‑utterance test set, roughly half the error rate of the base model. The model runs in audio.cpp with true token‑by‑token streaming.
Good at
- Egyptian Arabic transcription
- Arabic↔English code‑switching
- True token‑by‑token streaming
Limits
- No vision support
- Requires GPU with tensor cores for streaming
- License is Apache‑2.0
Best for
- Transcribing Egyptian Arabic podcasts
- Generating subtitles for Arabic/English bilingual videos
- Building voice‑assistant demos in Egypt
Who it’s for. Developers and researchers needing accurate Egyptian Arabic ASR or code‑switching support. The model is suitable for offline and streaming use via audio.cpp or vLLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| F16 | 4.1 GB | 5.1 GB | Fits | Get file → |
For 8 GB VRAM, use the Q8_0 quantization (2.48 GB file, ~3.3 GB memory at 8k context). For 12 GB VRAM, the F16 quant (4.09 GB file, ~5.1 GB memory) provides higher precision. Memory estimates are approximate.
What GPU do you need for .QwenCleo-ASR-gguf-root?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (4.1 GB file, about 5.1 GB in use).
Which .QwenCleo-ASR-gguf-root quant should you choose?
Q8_0 (2.5 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 .QwenCleo-ASR-gguf-root
How much VRAM does .QwenCleo-ASR-gguf-root need?
About 3.3 GB at Q8_0 with an 8K context window. That is the 2.5 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 .QwenCleo-ASR-gguf-root on an 8 GB GPU?
Yes, with F16: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of .QwenCleo-ASR-gguf-root GGUF?
It depends on the quant: Q8_0 is 2.5 GB, F16 is 4.1 GB.
Where can I download .QwenCleo-ASR-gguf-root GGUF?
The files are on Hugging Face in the mohammedaly22/QwenCleo-ASR-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 .QwenCleo-ASR-gguf-root 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 QwenCleo-ASR on 8 GB VRAM?
Yes, the Q8_0 quantized model fits 8 GB VRAM with about 3.3 GB memory usage at 8k context.
Does the model support vision tasks?
No, QwenCleo-ASR is an audio-only model.
Is the model open source?
Yes, it is released under the Apache‑2.0 license.