# Qwen3.5

Hybrid full-attention and gated-delta semantic lowering for Qwen3.5-4B.

[View canonical HTML](https://pllm.run/sdk/build/models/qwen35/)

Document ID: `pllm.docs.models.qwen35`  
Release: `0.1.0`

`pllm.qwen3_5_text.v1` lowers the text decoder in `Qwen/Qwen3.5-4B` revision `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`. The upstream configuration SHA-256 is `ddc63e1c717afa86c865bb5e01313d89d72bb53b97ad4a8a03ba8510c0621670`; the checked fixture adds one repository newline and is verified against both representations.

The plan retains the exact 3:1 linear/full layer schedule. Linear layers represent fused input projection, causal convolution state, Q/K L2 normalization, gated-delta decay and update, recurrent matrix state, and gated RMS normalization. Full-attention layers represent doubled query projection, Q/K normalization, partial multimodal rotary sections, KV state, and output gating. MTP configuration remains identity-bound but outside the base decoder graph.

These newly explicit operators currently report missing compiler coverage. Semantic lowering does not claim an executable Qwen3.5 runtime, checkpoint importer, generation quality, or protected recurrent protocol.

## Python SDK example

```python
from pathlib import Path

from pllm import lower_model

fixture = Path("crates/pllm-models/tests/fixtures/Qwen3.5-4B-851bf6e-config.json")
plan = lower_model(fixture.read_bytes(), batch=1, max_input_tokens=16, max_new_tokens=4)
operations = {operation["id"]: operation for operation in plan.prefill["operations"]}
assert operations["layer.0.linear_attention.gated_delta_rule"]["operator"] == "gated_delta_rule"
assert operations["layer.3.self_attention.q_rope"]["attributes"]["mrope_section"] == (11, 11, 10)
```

API: [Python SDK objects and signatures](/sdk/reference/python/pllm/#objects-and-signatures)

Run this example from a PLLM source checkout; package installations do not include
the pinned fixture. Inspecting its plan is not an execution claim.