Model reference · open weights
Qwen3.6-DFlash is an open-weight language model from z-lab. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | z-lab |
|---|---|
| Type | Language models |
| Task | Text gen |
| Parameters (lead) | 1.7B |
| Context | 256k tokens |
| Runs with | transformers |
| Released | 2026-04-23 |
| Popularity | 150k downloads / month |
| Licence | Open weights |
About
This model is still under training, and inference engine support may not be fully available yet due to architectural changes, including causal SWA layers.
DFlash is a novel speculative decoding method that utilizes a lightweight block diffusion model for drafting. It enables efficient, high-quality parallel drafting that pushes the limits of inference speed.
This model is the drafter component. It must be used in conjunction with the target model Qwen/Qwen3.6-27B.
vLLM (We temporarily modify the installation through this PR to support interleaved SWA and ensure correct handling of target hidden states for optimal performance):
uv pip install vllm
uv pip install -U --torch-backend=auto "vllm @ git+https://github.com/vllm-project/vllm.git@refs/pull/40898/head"
SGLang:
uv pip install "git+https://github.com/sgl-project/sglang.git@refs/pull/23000/head#subdirectory=python"
vLLM:
vllm serve Qwen/Qwen3.6-27B \
--speculative-config '{"method": "dflash", "model": "z-lab/Qwen3.6-27B-DFlash", "num_speculative_tokens": 15}' \
--attention-backend flash_attn \
--max-num-batched-tokens 32768
SGLang:
# Optional: enable schedule overlapping (experimental, may not be stable)
# export SGLANG_ENABLE_SPEC_V2=1
# export SGLANG_ENABLE_DFLASH_SPEC_V2=1
# export SGLANG_ENABLE_OVERLAP_PLAN_STREAM=1
python -m sglang.launch_server \
--model-path Qwen/Qwen3.6-27B \
--speculative-algorithm DFLASH \
--speculative-draft-model-path z-lab/Qwen3.6-27B-DFlash \
--speculative-num-draft-tokens 16 \
--tp-size 1 \
--attention-backend fa3 \
--mem-fraction-static 0.75 \
--mamba-scheduler-strategy extra_buffer \
--trust-remote-code
from openai import OpenAI
client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")
response = client.chat.completions.create(
model="Qwen/Qwen3.6-27B",
messages=[{"role": "user", "content": "Write a quicksort in Python."}],
max_tokens=4096,
temperature=0.0
)
print(response.choices[0].message.content)
N/A
Special thanks to David Wang for his outstanding engineering support on this project. We are also grateful to Modal, InnoMatrix, and Yotta Labs for providing the compute resources used to train this draft model.
If you find DFlash useful, please cite our work. To share feedback on DFlash or request new model support, please fill out this form: DFlash Feedback.
@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}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys qwen3-6-dflash for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen3-6-dflash below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3-6-dflash","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.