Instructions to use RadixArk/Qwen3.8-27B-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RadixArk/Qwen3.8-27B-DSpark with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True)
model = AutoModel.from_pretrained("RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RadixArk/Qwen3.8-27B-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RadixArk/Qwen3.8-27B-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RadixArk/Qwen3.8-27B-DSpark

SGLang

How to use RadixArk/Qwen3.8-27B-DSpark with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RadixArk/Qwen3.8-27B-DSpark" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RadixArk/Qwen3.8-27B-DSpark" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RadixArk/Qwen3.8-27B-DSpark with Docker Model Runner:
```
docker model run hf.co/RadixArk/Qwen3.8-27B-DSpark
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.8-27B-DSpark

A DSpark speculator for Qwen/Qwen3.8-27B-FP8. DSpark extends DFlash with target-model auxiliary features and a confidence head that dynamically chooses the number of draft tokens. The model was trained with SpecForge and is served with SGLang.

Model specifications

Target model: Qwen/Qwen3.8-27B-FP8
Checkpoint: epoch_2_step_4166
Draft parameters: 1,359,284,737 (1.36B)
Draft weight dtype: BF16
Hidden size: 5,120
Transformer layers: 5 full-attention layers
Attention: GQA with 40 query heads and 8 key/value heads
Target auxiliary feature layers: 4, 16, 28, 40, 52
Confidence head: vanilla Markov head, rank 256
DSpark block size: 7 draft tokens (verify width 8, including the target bonus token)
Maximum position embeddings: 262,144

Acceptance length

Acceptance length is the mean number of tokens accepted per speculative verification step, including the target bonus token. Each workload value below is the unweighted mean of SGLang's per-request spec_accept_length values.

Setting: FP8 target and unquantized BF16 draft; DSpark block size 7; sampling temperature 0.6, top-k 20, top-p 0.95; thinking enabled; max_new_tokens=2048; seed 0; up to 128 prompts per workload, or the full set when smaller. The prompt construction and measurement loop follow z-lab/dflash's SGLang benchmark path.

Workload	Acceptance length
HumanEval	3.47
GSM8K	4.57
MATH-500	4.08
LiveCodeBench	2.94
MBPP	3.67
AIME 2025	3.28
LBPP	3.03
AIME 2026	3.07
MT-Bench	3.10
Arena-Hard-v2	2.71
Alpaca	2.95

The evaluation contains 1,164 requests. The mean across all requests is 3.39, and the macro mean across the 11 workload means is 3.35. Every response contained acceptance statistics, and recomputing completion_tokens / spec_verify_ct matched spec_accept_length exactly.

Serving with SGLang

Use an SGLang version containing DSPARK support (the results above used the pinned main-branch commit shown in the evaluation setting):

sglang serve \
  --trust-remote-code \
  --model-path Qwen/Qwen3.8-27B-FP8 \
  --tp-size 1 \
  --speculative-algorithm DSPARK \
  --speculative-draft-model-path RadixArk/Qwen3.8-27B-DSpark \
  --speculative-dspark-block-size 7 \
  --speculative-draft-model-quantization unquant \
  --mamba-scheduler-strategy extra_buffer \
  --attention-backend fa3