Skip to content

Adding Support for Qwen3.5 & Qwen3.5 MoE (Text-only) #97

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
davidkoski merged 1 commit into from
Feb 27, 2026
Merged

Adding Support for Qwen3.5 & Qwen3.5 MoE (Text-only) #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion ACKNOWLEDGMENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@

MLX Swift was developed with contributions from the following individuals:

- [John Mai](https://github.com/johnmai-dev): Added support for multiple models (Qwen2, Starcoder2, InternLM2, Qwen3, Qwen3 MoE, GLM-4, MiMo, BitNet, SmolLM3, LFM2, Baichuan-M1).
- [John Mai](https://github.com/johnmai-dev): Added support for multiple models (Qwen2, Starcoder2, InternLM2, Qwen3,
Qwen3 MoE, GLM-4, MiMo, BitNet, SmolLM3, LFM2, Baichuan-M1, GPT-OSS, FalconH1, Exaone4, Qwen3.5, Qwen3.5 MoE).
- [Christoph Rohde](https://github.com/CodebyCR): Improved Embedders documentation.

<a href="https://github.com/ml-explore/mlx-swift-lm/graphs/contributors">
Expand Down
2 changes: 2 additions & 0 deletions Libraries/MLXLLM/LLMModelFactory.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,8 @@ public enum LLMTypeRegistry {
"qwen3": create(Qwen3Configuration.self, Qwen3Model.init),
"qwen3_moe": create(Qwen3MoEConfiguration.self, Qwen3MoEModel.init),
"qwen3_next": create(Qwen3NextConfiguration.self, Qwen3NextModel.init),
"qwen3_5": create(Qwen35Configuration.self, Qwen35Model.init),
"qwen3_5_moe": create(Qwen35Configuration.self, Qwen35MoEModel.init),
"minicpm": create(MiniCPMConfiguration.self, MiniCPMModel.init),
"starcoder2": create(Starcoder2Configuration.self, Starcoder2Model.init),
"cohere": create(CohereConfiguration.self, CohereModel.init),
Expand Down
Loading
Loading