QW

Qwen3 ASR 1.7B

QwenGGUF by ggml-orgUpdated 2026-04-13
Download on Hugging Face
Parameters2.03B
Context64K
Layers28
Architectureqwen3vl
Smallest quant2.2 GB
Quick answer

Qwen3 ASR 1.7B needs about 3.6 GB of memory at Q8_0 (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.2 GB (Q8_0) to 4.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Qwen3 ASR 1.7B – a 2‑billion‑parameter speech recognition model

Qwen3 ASR 1.7B is a 2‑billion‑parameter model trained for automatic speech recognition. It supports 52 languages and dialects and can perform language identification and ASR in a single model. The model is available in GGUF format and can be run with llama.cpp or other inference engines.

Good at

  • Speech recognition in 52 languages
  • Language identification
  • Long‑audio transcription

Limits

  • Requires 3.6 GB VRAM for Q8_0 at 8 k context
  • No vision support beyond speech
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Transcribing podcasts
  • Building multilingual voice assistants
  • Processing long audio files

Who it’s for. Developers needing an open‑source ASR model with broad language coverage. The model is suitable for research, prototyping, and production systems that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.2 GB 3.6 GB
Fits Get file →
BF164.1 GB 5.5 GB
Fits Get file →

For systems with 8 GB VRAM, use the Q8_0 quantization (2.17 GB file, ~3.6 GB VRAM). If more VRAM is available, the BF16 quant (4.07 GB file, ~5.5 GB VRAM) offers higher precision. Both are supported by llama.cpp.

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 (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 (2.2 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (4.1 GB file, about 5.5 GB in use).

Which Qwen3 ASR 1.7B quant should you choose?

Q8_0 (2.2 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

Architectureqwen3vl
Parameters2.03B
Layers28
Trained context65,536 tokens
KV cache (fp16)112 KB per token

Source

Quantized byggml-org
FamilyQwen
Licenseapache-2.0
Downloads (HF)40,361
Last updated2026-04-13

Frequently asked questions about Qwen3 ASR 1.7B

How much VRAM does Qwen3 ASR 1.7B need?

About 3.6 GB at Q8_0 with an 8K context window. That is the 2.2 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 BF16: the 4.1 GB file needs about 5.5 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: Q8_0 is 2.2 GB, BF16 is 4.1 GB.

What context length does Qwen3 ASR 1.7B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). 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 Qwen3 ASR 1.7B GGUF?

The files are on Hugging Face in the ggml-org/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 Q8_0 quantization requires about 3.6 GB VRAM at 8 k context, which fits in 8 GB. The BF16 quant needs ~5.5 GB VRAM.

Does the model support vision tasks?

No, the model only supports speech recognition and language identification.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-ASR-1.7B

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Qwen models

All Qwen →

Other tiny models

All tiny models →