Skip to content

Qwen3.5-4B is much slower than Qwen3-4B for INT4 text mode [webgpu] #2095

Description

@daijh

The Problem: Despite its new "Linear Attention" architecture (Gated Delta Networks) designed for high efficiency, the Qwen3.5-4B model is performing much slower than the older Qwen3-4B (21.0 tokens/s vs. 34.5 tokens/s).

The Cause: The current model builder forces the majority of layers (192 out of 249) into INT8 precision instead of INT4.

MatMulNBits Summary

Precision Type Count
INT4 57
INT8 192
Total 249

The Fix: By implementing PR #2094 (setting linear_attention_int8 to false by default), we can restore performance to a level similar to Qwen3-4B with no noticeable loss in output quality.

Performance at a Glance

Model Version Decode Speed Status
Qwen3-4B (Old) 34.5 tokens/s Baseline
Qwen3.5-4B (Current) 21.0 tokens/s ⚠️ Regression
Qwen3.5-4B (With Fix) 28.8 tokens/s Optimized

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions