Downloads · 30 days
0
Qwen3-ASR-0.6B-chatllm-quantized
Luigi/Qwen3-ASR-0.6B-chatllm-quantized
Qwen3-ASR-0.6B-chatllm-quantized is a machine learning model from Luigi. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains pre-quantized binaries for Qwen/Qwen3-ASR-0.6B optimized for use with chatllm.cpp and other GGML-compatible backends.
Access
Public
Updated Feb 8, 2026
Repo size
7.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin7.9 GB · 100%
At a glance
- Access
- Public
- Created
- Feb 5, 2026
- Updated
- Feb 8, 2026
- SHA
- bd34faae
Model card
From the Hugging Face model README
Qwen3-ASR-0.6B-chatllm-quantized
This repository contains pre-quantized binaries for Qwen/Qwen3-ASR-0.6B optimized for use with chatllm.cpp and other GGML-compatible backends.
Available Models
qwen3-asr-0.6b-q4_0.bin: 4-bit quantization (Decent accuracy, fastest inference). Recommended for free-tier CPU instances.qwen3-asr-0.6b-q8_0.bin: 8-bit quantization (High accuracy, slightly slower than Q4).
Usage with chatllm.cpp
- Clone or download the binaries.
- Run with the following command (requires
chatllm-main):
./chatllm-main -m qwen3-asr-0.6b-q4_0.bin -p audio.wav -n 2
Credits
- Original Model: Qwen Team (Alibaba Cloud)
- C++ Backend: foldl/chatllm.cpp
- Quantization: Pre-quantized using
chatllm.cppconversion scripts.
License
Please refer to the original Qwen3-ASR License.
- Created
- Feb 5, 2026
- Updated
- Feb 8, 2026