8-bit Open on Hugging Face
Parameters
2.0B
Weights (est.)
≈ 2.5 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- netease-youdao/Confucius4-R2T2 (quantized)
- Vendor
- netease-youdao
- Task
- Speech recognition
- Quantisation
- 8-bit
- Licence
- netease-youdao-model-use-license-agreement
- Downloads
- 166 in the last 30 days · 579 all time · 4 likes
- Published
- 2026-09-22 · updated 2026-09-22 (1mo ago)
- Languages
- zh, en
- Tags
- qwen3_asr, mlx-audio, streaming, confucius4, r2t2
Other MLX builds of netease-youdao/Confucius4-R2T2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Confucius4-R2T2-8bit (this one) | 8-bit | ≈ 2.5 GB | 8 GB+ | 166 |
| Confucius4-R2T2-bf16 | bf16 | ≈ 4.1 GB | 8 GB+ | 40 |