Instructions to use RadixArk/Qwen3.8-2.4T-A95B-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RadixArk/Qwen3.8-2.4T-A95B-DSpark with Transformers:

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

pipe = pipeline("text-generation", model="RadixArk/Qwen3.8-2.4T-A95B-DSpark", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("RadixArk/Qwen3.8-2.4T-A95B-DSpark", trust_remote_code=True)
model = AutoModel.from_pretrained("RadixArk/Qwen3.8-2.4T-A95B-DSpark", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RadixArk/Qwen3.8-2.4T-A95B-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RadixArk/Qwen3.8-2.4T-A95B-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/Qwen3.8-2.4T-A95B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RadixArk/Qwen3.8-2.4T-A95B-DSpark

SGLang

How to use RadixArk/Qwen3.8-2.4T-A95B-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/Qwen3.8-2.4T-A95B-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/Qwen3.8-2.4T-A95B-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/Qwen3.8-2.4T-A95B-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/Qwen3.8-2.4T-A95B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RadixArk/Qwen3.8-2.4T-A95B-DSpark with Docker Model Runner:
```
docker model run hf.co/RadixArk/Qwen3.8-2.4T-A95B-DSpark
```

Qwen3.8-Max DSpark speculator

A DSpark speculator for RadixArk/Qwen3.8-2.4T-A95B-NVFP4. DSpark extends the DFlash parallel-draft backbone with a Markov logit-bias head and a per-position confidence head. Trained with SpecForge online distillation from hidden states captured off a live SGLang target engine.

Model specifications

Base model: RadixArk/Qwen3.8-2.4T-A95B-NVFP4 (92-layer hybrid-attention MoE, hidden size 8192)
Format: single-file BF16 safetensors, 3,298,141,697 parameters
Draft: 5 full-attention Qwen3-style GQA layers, hidden size 8192, 64 query heads / 8 KV heads at head_dim 128, block_size=7
Verification width: 1 current token + 7 draft tokens
Auxiliary target layers: [3, 19, 35, 55, 71, 87], plus the final post-norm hidden state
Positional scheme: YaRN factor 32 with original length 8,192 — 262,144 addressable positions, the target's native context limit
Target weights: embedding and unembedding weights are not included

Acceptance length

Accept length is the mean number of accepted tokens per verify step including the bonus token (SGLang spec_accept_length), averaged over requests. Setting: SGLang DSPARK serving, TP8 on one 8xB300 node, NVFP4 target, BF16 draft (--speculative-draft-model-quantization unquant), block size 7; sampling temperature 0.6, top_k 20, top_p 0.95, thinking enabled; max_new_tokens 2048; 128 prompts per workload (full set where the dataset is smaller). The measurement loop follows z-lab/dflash benchmark.py.

Workload	Accept length	Prompts
humaneval	5.30	128
gsm8k	4.89	128
math500	4.85	128
livecodebench	4.72	128
mbpp	4.52	128
aime25	4.43	30
lbpp	4.40	128
aime26	4.35	30
mtbench	3.43	80
arena_hard_v2	3.22	128
alpaca	3.05	128

Serving with SGLang

sglang serve \
  --trust-remote-code \
  --model-path RadixArk/Qwen3.8-2.4T-A95B-NVFP4 \
  --tp-size 8 \
  --speculative-algorithm DSPARK \
  --speculative-draft-model-path RadixArk/Qwen3.8-2.4T-A95B-DSpark \
  --speculative-dspark-block-size 7 \
  --speculative-draft-attention-backend trtllm_mha

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Collections including RadixArk/Qwen3.8-2.4T-A95B-DSpark

DSpark

Collection

5 items • Updated about 9 hours ago

Qwen3.8

Collection

2 items • Updated about 9 hours ago