Downloads · 30 days
1.1K
22% of all-time downloads
qwen3-asr-gguf
Alkd/qwen3-asr-gguf
qwen3-asr-gguf is a machine learning model from Alkd. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
GGUF-quantized weights for Qwen3-ASR, a Rust inference engine for the Qwen3 audio speech recognition model built with candle.
All-time downloads
5K
Public
Repo size
6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf6 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- 06a21d59
Model card
From the Hugging Face model README
Qwen3-ASR GGUF
GGUF-quantized weights for Qwen3-ASR, a Rust inference engine for the Qwen3 audio speech recognition model built with candle.
Files
| File | Size | Quant | Accuracy (short samples) |
|---|---|---|---|
qwen3_asr_0.6b_q8_0.gguf | 966 MB | Q8_0 | 2/2 ✓ |
qwen3_asr_0.6b_q4_0.gguf | 521 MB | Q4_0 | 1/2 (expected 4-bit degradation) |
qwen3_asr_0.6b_q4_k.gguf | 577 MB | Q4_K | 1/2 (expected 4-bit degradation) |
qwen3_asr_1.7b_q8_0.gguf | 2.3 GB | Q8_0 | 2/2 ✓ |
qwen3_asr_1.7b_q4_k.gguf | 1.2 GB | Q4_K | 2/2 ✓ |
Usage
cargo run --release -- --gguf qwen3_asr_1.7b_q4_k.gguf
See qwen3-asr-rs for full documentation.
Quantization Notes
- Q8_0: 8-bit symmetric, block=32. Closest to original BF16 quality.
- Q4_0: 4-bit symmetric, block=32. Split-half nibble packing (ggml-compatible).
- Q4_K: 4-bit K-quant, super-block=256 with per-sub-block scale/min. Tensors with
shape[-1] % 256 ≠ 0fall back to Q8_0 automatically (affects 0.6B audio encoder, d_model=896).
The 1.7B Q4_K model retains full accuracy (2/2) while reducing size from 2.3 GB to 1.2 GB.
- License
- apache-2.0
- Languages
- en, zh
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026