Maker

Alibaba Apple Silicon Benchmarks

Vision-language and speech weights from Alibaba's Qwen team. GroundSlate runs the MLX conversions from mlx-community: Qwen3-VL describes footage, Qwen3-TTS speaks.

qwenlm.github.io

Qwen3-VL

Qwen3-VL is Alibaba's vision-language line. GroundSlate runs the 4-bit MLX conversions from mlx-community.

Alibaba · Qwen3-VL

Qwen3-VL 4B

mlx-community/Qwen3-VL-4B-Instruct-4bit

3.1 GB

Alibaba · Qwen3-VL

Qwen3-VL 8B

mlx-community/Qwen3-VL-8B-Instruct-4bit

5.8 GB

Qwen3-TTS is Alibaba's speech line. The 12 Hz in every repo name is its audio token rate. GroundSlate installs four checkpoints for two jobs: a Base checkpoint speaks your scripts, and a CustomVoice or VoiceDesign checkpoint makes a voice once and is not used after that.

Default

Alibaba · Qwen3-TTS

Qwen3-TTS 1.7B

mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit

2.3 GB