mlx-community
/

Qwen3.5-4B-nvfp4

4-bit precision

Model card Files Files and versions

Qwen3.5-4B-nvfp4

3.06 GB

1 contributor

History: 2 commits

machiabeli's picture

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4

e9e620e verified about 7 hours ago

.gitattributes
1.57 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
chat_template.jinja
7.76 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
config.json
3.36 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
model.safetensors
3.03 GB
xet

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
model.safetensors.index.json
80.1 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
preprocessor_config.json
390 Bytes

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
processor_config.json
1.3 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
tokenizer.json
20 MB
xet

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
tokenizer_config.json
1.14 kB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
video_preprocessor_config.json
385 Bytes

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago
vocab.json
6.72 MB

Convert Qwen3.5 to MLX Qwen3.5-4B-nvfp4 about 7 hours ago