Qwen3.5-9B-DFlash-GGUF

Quantized version of z-lab/Qwen3.5-9B-DFlash.

Works with mainline llama.cpp, will NOT work with forks.

Their model card is pasted as is below.

Files:

• model.safetensors - original unquantized safetensors
• model.gguf - unquantized bf16 GGUF
• Qwen3.5-9B-DFlash.gguf - GGUF quantized to Q5_K_M

---

Qwen3.5-9B-DFlash

Paper | Github | Blog

This DFlash draft model is a joint retrain from Z-Lab and Modal, trained with 40k sequence length and sliding-window attention for improved long-context performance. It is mirrored across the following Hugging Face repositories:

• z-lab/Qwen3.5-9B-DFlash
• modal-labs/Qwen3.5-9B-DFlash

This repository contains a DFlash draft model for Qwen/Qwen3.5-9B. It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server.

DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution.

<div align="center"> <img src="assets/dflash_system.png" alt="DFlash Architecture" width="85%"> </div>

Quick Start

Installation

SGLang

Install a recent SGLang build with DFlash support:

uv pip install --upgrade "sglang[all]"

For best performance on Blackwell GPUs, use an SGLang build that includes DFlash, FA4/TRT-LLM attention, and FlashInfer support.

vLLM

For vLLM support, please refer to vllm-project/vllm#40898. We will update the PR to make it merge-ready soon.

Launch Server

This model should be used with an inference server that supports DFlash speculative decoding. An example SGLang deployment is:

export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1

python -m sglang.launch_server \
  --model-path Qwen/Qwen3.5-9B \
  --trust-remote-code \
  --speculative-algorithm DFLASH \
  --speculative-draft-model-path z-lab/Qwen3.5-9B-DFlash \
  --speculative-dflash-block-size 8 \
  --speculative-draft-attention-backend fa4 \
  --attention-backend trtllm_mha \
  --linear-attn-prefill-backend flashinfer \
  --linear-attn-decode-backend flashinfer \
  --mamba-scheduler-strategy extra_buffer \
  --tp-size 1 \
  --max-running-requests 32 \
  --cuda-graph-max-bs-decode 32 \
  --cuda-graph-backend-prefill tc_piecewise \
  --enable-flashinfer-allreduce-fusion \
  --mem-fraction-static 0.8 \
  --host 0.0.0.0 \
  --port 30000

Block size 8 is the recommended default for higher-concurrency serving. Block size 16 gives longer accept lengths and strong concurrency-1 throughput in most workloads.

Benchmark Results

We benchmarked DFlash against the autoregressive baseline and Qwen's built-in MTP draft path. DFlash reaches up to 5.01x speedup at concurrency 1 and 2.58x at concurrency 32. Across the benchmark suite, DFlash delivers higher throughput than MTP at every matched setting where both completed.

Setup

• Runtime: SGLang on 1x NVIDIA B200 GPU, tensor parallel size 1, bfloat16
• Backends: trtllm_mha target attention, fa4 DFlash draft attention, flashinfer linear-attention prefill and decode
• Workloads: GSM8K, MATH500, HumanEval, MBPP, and MT-Bench with the Qwen chat template
• Decoding: greedy, thinking enabled, max output length 4096 tokens
• Measurement: 5 independent runs per configuration at concurrency 1 and 32 with continuous batching
• Throughput: generated output tokens / wall-clock benchmark time, including prefill and scheduling
• Accept length: completion_tokens / spec_verify_ct per generation turn, averaged across generation turns

Throughput and Speedup

Each cell is output tok/s (speedup). Bold marks the fastest speculative configuration in each row.

Concurrency 1

Concurrency 32

Accept Length

Mean accept length at concurrency 1. Bold marks the higher value in each matched MTP/DFlash pair.

Citation

If you find DFlash useful, please cite the original paper:

@article{chen2026dflash,
  title   = {{DFlash: Block Diffusion for Flash Speculative Decoding}},
  author  = {Chen, Jian and Liang, Yesheng and Liu, Zhijian},
  journal = {arXiv preprint arXiv:2602.06036},
  year    = {2026}
}