software-mansion
/

Qwen3-ExecuTorch

Text Generation

Model card Files Files and versions

Qwen3-ExecuTorch / 0_6b /mlx

Commit History

Oct 15 15 days ago

14:11
fix(0_6b/mlx): re-export with RNE fork MLX serialization (opcode 122)

Bartosz Hanc

764c9b7

Oct 14 16 days ago

18:19
fix(0_6b/mlx): update get_eos_ids metadata to include 151643 (<|endoftext|>)

Bartosz Hanc

8facbb9
17:44
docs: update model card, context lengths, and config specs

Bartosz Hanc

5792d81
16:50
Update Qwen 3 0.6B MLX model to int8 (v0.11.0)

Bartosz Hanc

0dcb84e

Oct 12 18 days ago

13:02
update models

bhanc

738a5fe

Sep 5

20:32
Add MLX int4 variants for 0.6B, 1.7B and 4B

msluszniak

Verified signature
fa72381