Skip to content

v0.10.0: Qwen3.5-35B-A3B support

Latest
Latest

Choose a tag to compare

View all tags
@Hmbown Hmbown released this 03 Mar 21:20
· 2 commits to main since this release
v0.10.0
c124599

What's New

Qwen3.5-35B-A3B MoE decode support — patch(model) now auto-detects Qwen3.5's hybrid DeltaNet+Attention architecture (256 experts, K=8) and applies fused MoE decode kernels.

Measured results (M4 Max 36GB, stock MLX)

Model Decode Prefill Fidelity
Qwen3.5-35B-A3B-4bit ~+2% ~+4% token-identical
LFM2-8B-A1B-4bit +12.8% neutral token-identical
LFM2-24B-A2B-4bit +6.0% neutral token-identical

Results will vary depending on hardware, thermal state, and prompt length.

Also in this release

  • DeltaNet pattern: fuses conv1d + silu for Qwen3.5 GatedDeltaNet decode layers (30 of 40 layers)
  • Expert index sorting (opt-in): ZMLX_MOE_SORT_EXPERTS=1 for DRAM locality experiments
  • README cleanup: consolidated benchmark sections into a single results table
  • 150+ benchmark repro capsules from GLM/Qwen3 isolation sweeps and consistency checks
  • New tests: 23 DeltaNet kernel tests + 8 patch tests + fusion/integration tests

Install / upgrade

pip install --upgrade zmlx

Full changelog

See CHANGELOG.md

Assets 2
Loading