YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Qwen3.5-2B text-only 4-bit for NoteTkr
Deterministically derived from mlx-community/Qwen3.5-2B-4bit at 674aaa7240b91e8012fcad5d791b7dfe5ba90207
using NoteTkr recipe qwen3.5-text-only-v1. Architecture: qwen3_5_text.
All language tensors retain their original dtype, shape and payload bytes, including
4-bit weights, scales and biases. Only vision_tower.* tensors are removed;
language_model. is stripped from decoder names. No requantization or training.
Tokenizer files and chat template are unchanged, including reserved vocabulary.
Upstream model: Qwen/Qwen3.5-2B. License: Apache-2.0. This is a locally derived package; its content revision is not a Hugging Face commit.
- Downloads last month
- 13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support