Instructions to use RigCodeAI/Qwen3.6-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RigCodeAI/Qwen3.6-35B-A3B with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("RigCodeAI/Qwen3.6-35B-A3B")
config = load_config("RigCodeAI/Qwen3.6-35B-A3B")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use RigCodeAI/Qwen3.6-35B-A3B with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RigCodeAI/Qwen3.6-35B-A3B"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RigCodeAI/Qwen3.6-35B-A3B"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RigCodeAI/Qwen3.6-35B-A3B with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RigCodeAI/Qwen3.6-35B-A3B"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default RigCodeAI/Qwen3.6-35B-A3B

Run Hermes

hermes

OpenClaw new

How to use RigCodeAI/Qwen3.6-35B-A3B with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RigCodeAI/Qwen3.6-35B-A3B"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "RigCodeAI/Qwen3.6-35B-A3B" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.6-35B-A3B / speculative /README.md

jacobpwarren

Upload folder using huggingface_hub

0e02365 verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

5.84 kB

metadata

license: mit
library_name: transformers
pipeline_tag: text-generation
tags:
  - dflash
  - speculative-decoding
  - block-diffusion
  - draft-model
  - efficiency
  - qwen
  - diffusion-language-model

Qwen3.6-35B-A3B-DFlash

Paper | GitHub | Blog

DFlash is a speculative decoding method that uses a lightweight block diffusion model to draft multiple tokens in parallel. This is the drafter model, which must be paired with Qwen/Qwen3.6-35B-A3B.

Quick Start

Installation

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/20547/head#subdirectory=python"

Launch Server

vLLM:

vllm serve Qwen/Qwen3.6-35B-A3B \
  --speculative-config '{"method": "dflash", "model": "z-lab/Qwen3.6-35B-A3B-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/Qwen3.6-35B-A3B \
    --speculative-algorithm DFLASH \
    --speculative-draft-model-path z-lab/Qwen3.6-35B-A3B-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

Tip: For long-context or agentic workloads, add --speculative-dflash-draft-window-size WINDOW_SIZE to enable sliding-window attention for the drafter.

Usage

from openai import OpenAI

client = OpenAI(base_url="http://localhost:30000/v1", api_key="EMPTY")

response = client.chat.completions.create(
    model="Qwen/Qwen3.6-35B-A3B",
    messages=[{"role": "user", "content": "Write a quicksort in Python."}],
    max_tokens=4096,
    temperature=0.0
)
print(response.choices[0].message.content)

Benchmark Results

Setup: Single NVIDIA B200, SGLang, thinking enabled, max output length 4096. We report end-to-end throughput, including prefill time. See our GitHub repository for reproduction scripts.

Throughput and Speedup

DFlash achieves up to 2.9x speedup at concurrency 1.

Tokens/sec (speedup vs. autoregressive baseline)

Block Size = 16

Task	Concurrency	AR	DFlash
Math500	1	234	682 (2.9x)
	8	1266	3138 (2.5x)
	16	1954	4813 (2.5x)
	32	2755	6520 (2.4x)
GSM8K	1	235	556 (2.4x)
	8	1236	2564 (2.1x)
	16	1886	3821 (2.0x)
	32	2699	5239 (1.9x)
HumanEval	1	238	603 (2.5x)
	8	1255	2800 (2.2x)
	16	1944	4208 (2.2x)
	32	2767	5782 (2.1x)
MBPP	1	235	559 (2.4x)
	8	1224	2538 (2.1x)
	16	1948	3816 (2.0x)
	32	2780	5378 (1.9x)
MT-Bench	1	233	442 (1.9x)
	8	1238	2028 (1.6x)
	16	1885	2997 (1.6x)
	32	2633	4034 (1.5x)
Alpaca	1	235	393 (1.7x)
	8	1221	1782 (1.5x)
	16	1844	2567 (1.4x)
	32	2579	3689 (1.4x)

Block Size = 8

Task	Concurrency	AR	DFlash
Math500	1	234	617 (2.6x)
	8	1266	2839 (2.2x)
	16	1954	4465 (2.3x)
	32	2755	6614 (2.4x)
GSM8K	1	235	540 (2.3x)
	8	1236	2466 (2.0x)
	16	1886	3899 (2.1x)
	32	2699	5713 (2.1x)
HumanEval	1	238	561 (2.4x)
	8	1255	2655 (2.1x)
	16	1944	4135 (2.1x)
	32	2767	6059 (2.2x)
MBPP	1	235	497 (2.1x)
	8	1224	2324 (1.9x)
	16	1948	3636 (1.9x)
	32	2780	4884 (1.8x)
MT-Bench	1	233	438 (1.9x)
	8	1238	2060 (1.7x)
	16	1885	3182 (1.7x)
	32	2633	4720 (1.8x)
Alpaca	1	235	407 (1.7x)
	8	1221	1880 (1.5x)
	16	1844	2903 (1.6x)
	32	2579	4115 (1.6x)

Acceptance Length

Task	B8	B16
Math500	5.56	7.35
GSM8K	5.21	6.73
HumanEval	5.09	6.44
MBPP	4.78	5.83
MT-Bench	4.20	5.14
Alpaca	3.94	4.62

Acknowledgements

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.

Citation

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}
}