qwen3 asr 1.7b needs about 2.5 GB of memory at Q5_K (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.5 GB (Q4_0) to 4.7 GB (F16).
Qwen3-ASR 1.7B: Multilingual speech recognition up to 5 minutes
Qwen3-ASR 1.7B is a multilingual ASR model supporting 30 languages and 22 Chinese dialects. It handles speech, singing voice, and songs with background music. The model uses a 24‑layer Whisper‑style audio encoder and a 28‑layer Qwen3 decoder.
Good at
- Accurate transcription for 30 languages
- Handles singing and background music
- Supports up to 5 minutes of audio
Limits
- No vision support
- Requires 8‑k context for memory estimates
- License is Apache‑2.0
Best for
- Transcribing podcasts
- Generating subtitles for multilingual videos
- Speech‑to‑text in noisy environments
Who it’s for. Developers building multilingual ASR pipelines or content creators needing robust transcription. The model is suitable for both batch and streaming inference with CrispASR or llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q4_K | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q5_K | 1.7 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| F16 | 4.7 GB | 5.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K (file size 1.49 GB, estimated 2.2 GB memory). For 12 GB VRAM, Q5_K (1.74 GB, 2.5 GB memory) is a good balance. If more VRAM is available, Q8_0 (2.51 GB, 3.3 GB memory) or F16 (4.7 GB, 5.8 GB memory) provide higher precision.
What GPU do you need for qwen3 asr 1.7b?
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 (4.7 GB file, about 5.8 GB in use).
Which qwen3 asr 1.7b quant should you choose?
Q5_K (1.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwen3 asr 1.7b
How much VRAM does qwen3 asr 1.7b need?
About 2.5 GB at Q5_K with an 8K context window. That is the 1.7 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 qwen3 asr 1.7b on an 8 GB GPU?
Yes, with F16: the 4.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of qwen3 asr 1.7b GGUF?
It depends on the quant: Q4_0 is 1.5 GB, Q4_K is 1.5 GB, Q5_K is 1.7 GB, Q8_0 is 2.5 GB, F16 is 4.7 GB.
Where can I download qwen3 asr 1.7b GGUF?
The files are on Hugging Face in the cstr/qwen3-asr-1.7b-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 qwen3 asr 1.7b 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 Qwen3-ASR 1.7B on 8 GB VRAM?
Yes, the Q4_0 or Q4_K quantizations use about 2.2 GB of VRAM at 8‑k context, which fits within 8 GB.
Does the model support streaming inference?
Yes, it supports streaming and offline unified inference with a single model.
What license applies to the GGUF files?
The GGUF files are distributed under Apache‑2.0, the same license as the upstream model.