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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

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

MLX

How to use jialinyyzz/Qwen3.8-27B-DSpark-drafter with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("jialinyyzz/Qwen3.8-27B-DSpark-drafter")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

How to use jialinyyzz/Qwen3.8-27B-DSpark-drafter 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 "jialinyyzz/Qwen3.8-27B-DSpark-drafter" \
    --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": "jialinyyzz/Qwen3.8-27B-DSpark-drafter",
		"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 "jialinyyzz/Qwen3.8-27B-DSpark-drafter" \
        --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": "jialinyyzz/Qwen3.8-27B-DSpark-drafter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use jialinyyzz/Qwen3.8-27B-DSpark-drafter with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "jialinyyzz/Qwen3.8-27B-DSpark-drafter" --prompt "Once upon a time"

Docker Model Runner
How to use jialinyyzz/Qwen3.8-27B-DSpark-drafter with Docker Model Runner:
```
docker model run hf.co/jialinyyzz/Qwen3.8-27B-DSpark-drafter
```
Atomic Chat

Qwen3.8-27B-DSpark (mirror)

This is an unmodified mirror of RadixArk/Qwen3.8-27B-DSpark, re-hosted so the Qwen3.8-27B-abliterated-MLX-{8,4}bit models are self-contained for DSpark speculative decoding on Apple Silicon. All credit for the drafter goes to RadixArk. If the original repo is available, prefer it — mlx-dspark resolves it automatically.

Why it's here

DSpark speculative decoding needs two weights: the target model (the abliterated Qwen3.8-27B) and this ~1.36B drafter. mlx-dspark auto-downloads the drafter from RadixArk by default, so no manual assembly is needed. This mirror exists only as a fallback so the package keeps working even if the upstream repo moves.

Use with the abliterated MLX target

pip install mlx-dspark
# auto (uses RadixArk upstream): 
mlx-dspark generate --model ./Qwen3.8-27B-abliterated-MLX-8bit --mode dspark --prompt "..."
# explicit (uses this mirror): 
mlx-dspark generate --model ./Qwen3.8-27B-abliterated-MLX-8bit \
  --drafter ./Qwen3.8-27B-DSpark-drafter --mode dspark --prompt "..."

Note: this drafter was trained against the original Qwen3.8-27B. On the abliterated target it still produces correct output (the target verifies every token — speculative decoding is lossless), but the accepted-token rate may be a little lower on prompts the original model would have refused.

Original model card (RadixArk/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. Trained with SpecForge, served with SGLang.

Draft parameters: 1,359,284,737 (1.36B) · BF16 · hidden 5,120 · 5 full-attention layers · GQA 40Q/8KV
Target auxiliary feature layers: 4, 16, 28, 40, 52 · confidence head: Markov, rank 256
DSpark block size: 7 draft tokens (verify width 8) · max positions 262,144
Mean acceptance length across 11 workloads (SGLang, FP8 target): 3.35–3.39

Downloads last month: 892

Safetensors

Model size

1B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for jialinyyzz/Qwen3.8-27B-DSpark-drafter

Base model

Qwen/Qwen3.8-27B

Quantized

RadixArk/Qwen3.8-27B-NVFP4

Finetuned

RadixArk/Qwen3.8-27B-DSpark

Finetuned

(7)

this model