Just the multi-token-prediction (MTP) draft head from the official Qwen/Qwen3.5-4B checkpoint, packed into a single ~230 MiB safetensors file.

z-lab/Qwen3.5-4B-PARO declares mtp_num_hidden_layers: 1 in its config.json but ships zero mtp.* tensors in the safetensors. vLLM accordingly creates the draft module from random weights when --speculative-config '{"method": "mtp"}' is passed — the verifier rejects every drafted token (0% acceptance), so speculative decoding becomes pure overhead.

This repo provides the missing weights, extracted verbatim from the upstream BF16 base model with no modification.

Extracted verbatim from Qwen/Qwen3.5-4B (the public BF16 base model) by reading the two safetensors shards that contain mtp.* keys per model.safetensors.index.json and saving them to a single file. No weights were modified.

To verify yourself:

paroquant-inject-mtp is a small CLI that wires this MTP head into the paroquant model directory without copying its 14 GB of weights — symlinks the upstream LM safetensors and writes only the MTP shard:

Acceptance is lower than larger siblings (27B reaches ~92%) — the MTP head was trained against BF16 hidden states, and paroquant INT4 quantization noise affects predictions proportionally more on smaller models. Empirically the spec-decode net throughput gain may be marginal on the smallest sizes; benchmark for your workload before relying on it.

Apache 2.0, inherited from the upstream Qwen/Qwen3.5-4B LICENSE. This repo only redistributes a subset of upstream weights with no modification.

Authors: guru87 (GitHub: guru1987) and Claude Opus 4.7 (Anthropic, 1M context). Diagnosis, patches, scripting, and docs were developed collaboratively over a single session in May 2026.