Qwen3-14B-MLX-8bit
Qwen/Qwen3-14B-MLX-8bit
- kind
- mlx
- quant
- mlx
- family
- qwen
- modality
- text-generation
- root model
- Qwen/Qwen3-14B-Base
- provider
- Qwen
- license
- apache-2.0
- language
- —
- context
- 32,768
- library
- mlx
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 900
- likes
- 5
- created
- —
- last modified
- 2025-07-07T08:50:35+00:00 (2025)
- huggingface
- https://huggingface.co/Qwen/Qwen3-14B-MLX-8bit
- tags
- mlxsafetensorsqwen3text-generationconversationalarxiv:2309.00071arxiv:2505.09388base_model:Qwen/Qwen3-14B-Basebase_model:quantized:Qwen/Qwen3-14B-Baselicense:apache-2.08-bitregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.