QW

Qwen3 ASR 0.6B

QwenGGUF by mradermacherUpdated 2026-04-15
Download on Hugging Face
Parameters752M
Context64K
Layers28
Architectureqwen3vl
Smallest quant0.3 GB
Quick answer

Qwen3 ASR 0.6B needs about 1.9 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Qwen3 ASR 0.6B – 0.752B parameter speech recognition model

Qwen3 ASR 0.6B is a 0.752B parameter model that supports language identification and speech recognition for 52 languages and dialects. It is built on the Qwen3VL architecture and trained with 65536 context tokens. The model is released under the apache-2.0 license.

Good at

  • Speech recognition in 52 languages
  • Language identification
  • Forced alignment with timestamps

Limits

  • No vision support beyond audio
  • Requires 8k context for memory estimates
  • No proprietary API integration

Best for

  • Transcribing long audio streams
  • Batch ASR inference
  • Timestamp generation for speech

Who it’s for. Developers building multilingual ASR pipelines or researchers needing an open‑source model for speech recognition and language identification. The model is suitable for applications that require accurate transcription across diverse languages and dialects.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.8 GB
Fits Get file →
Q3_K_S0.4 GB 1.8 GB
Fits Get file →
Q3_K_M0.4 GB 1.9 GB
Fits Get file →
Q3_K_L0.4 GB 1.9 GB
Fits Get file →
IQ4_XS0.5 GB 1.9 GB
Fits Get file →
Q4_K_S0.5 GB 1.9 GB
Fits Get file →
Q4_K_M0.5 GB 1.9 GB
Fits Get file →
Q5_K_S0.5 GB 2.0 GB
Fits Get file →
Q5_K_M0.6 GB 2.0 GB
Fits Get file →
Q6_K0.6 GB 2.1 GB
Fits Get file →
Q8_00.8 GB 2.2 GB
Fits Get file →
F161.5 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.48 GB file, ~1.9 GB memory at 8k context) or Q5_K_S (0.54 GB file, ~2 GB memory). For 4 GB VRAM, use Q3_K_M (0.41 GB file, ~1.9 GB memory). For 2 GB VRAM, use Q2_K (0.35 GB file, ~1.8 GB memory).

What GPU do you need for Qwen3 ASR 0.6B?

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 F16 (1.5 GB file, about 2.9 GB in use).

Which Qwen3 ASR 0.6B quant should you choose?

Q4_K_M is the usual starting point for Qwen3 ASR 0.6B: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.7 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.

If memory is tight, the smallest file is Q2_K at 0.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3vl
Parameters752M
Layers28
Trained context65,536 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,157
Last updated2026-04-15

Frequently asked questions about Qwen3 ASR 0.6B

How much VRAM does Qwen3 ASR 0.6B need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Qwen3 ASR 0.6B on an 8 GB GPU?

Yes, with F16: the 1.5 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 Qwen3 ASR 0.6B GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB, IQ4_XS is 0.5 GB, Q4_K_S is 0.5 GB and 6 more.

What context length does Qwen3 ASR 0.6B 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 0.6B GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-ASR-0.6B-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 0.6B 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 0.6B on 8 GB VRAM?

Yes, using the Q4_K_M or Q5_K_S quantized files will fit within 8 GB VRAM with approximate memory usage of 1.9–2 GB at 8k context.

Does the model support forced alignment?

Yes, the model includes a forced alignment solution that predicts timestamps for up to 5 minutes of speech in 11 languages.

What license does the model use?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3-ASR-0.6B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →