Instructions to use vadery/Qwen3.5-0.8B-W8A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vadery/Qwen3.5-0.8B-W8A8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="vadery/Qwen3.5-0.8B-W8A8")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("vadery/Qwen3.5-0.8B-W8A8")
model = AutoModelForMultimodalLM.from_pretrained("vadery/Qwen3.5-0.8B-W8A8", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vadery/Qwen3.5-0.8B-W8A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vadery/Qwen3.5-0.8B-W8A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vadery/Qwen3.5-0.8B-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/vadery/Qwen3.5-0.8B-W8A8

SGLang

How to use vadery/Qwen3.5-0.8B-W8A8 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 "vadery/Qwen3.5-0.8B-W8A8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vadery/Qwen3.5-0.8B-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "vadery/Qwen3.5-0.8B-W8A8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vadery/Qwen3.5-0.8B-W8A8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use vadery/Qwen3.5-0.8B-W8A8 with Docker Model Runner:
```
docker model run hf.co/vadery/Qwen3.5-0.8B-W8A8
```

Qwen3.5-0.8B W8A8 (INT8 weights + INT8 dynamic activations)

W8A8 INT8 quantization of Qwen/Qwen3.5-0.8B, produced with llm-compressor (SmoothQuant + GPTQ). The built-in MTP head is preserved as BF16 and works in vLLM ≥ 0.17 out of the box.

Quick start

pip install "vllm>=0.17"
huggingface-cli download vadery/Qwen3.5-0.8B-W8A8 --local-dir ./Qwen3.5-0.8B-W8A8

vllm serve ./Qwen3.5-0.8B-W8A8 \
  --max-model-len 32768 \
  --dtype bfloat16 \
  --trust-remote-code \
  --reasoning-parser qwen3 \
  --speculative-config '{"method":"qwen3_5_mtp","num_speculative_tokens":1}'

No additional patches required — both config.json.quantization_config.ignore (covers MTP Linear modules) and actorder field are already fixed.

Performance (single H200 SXM, single-stream)

Workload	Throughput	TPOT p50	MTP Accept rate	Mean accept length
JSON gen (concurrency 1)	392 tok/s	2.6 ms	95.4 %	1.95 / 2.0

3-4× faster than the BF16 source running the same MTP recipe.

Architecture preserved

Component	Status
Language model Linear (q/k/v/o, MLP) on full-attn layers	INT8 (W8A8 channelwise weight + dynamic per-token activation)
`linear_attn.*` (Gated DeltaNet / SSM) layers	BF16 (excluded — Mamba state numerics matter)
Vision tower (`model.visual.*`)	BF16 (excluded)
MTP head (`mtp.*`, 1 layer)	BF16 (excluded; correctly listed in `quantization_config.ignore`)
`lm_head`, embeddings, norms	BF16 / FP32 (excluded)

Quantization recipe

SmoothQuantModifier(smoothing_strength=0.8, mappings=SQ_MAPPINGS,
                    ignore=[...vision, mtp, linear_attn, embed, lm_head...])
GPTQModifier(targets="Linear", scheme="W8A8",
             ignore=[same as above],
             dampening_frac=0.01)

SmoothQuant mappings explicitly cover only the 6 full-attention layers (indices 3, 7, 11, 15, 19, 23 out of 24) plus MLP on every layer — to avoid SmoothQuant trying to fuse into the linear_attn projections which have a non-standard shape.

Calibration: 256 samples × 2048 tokens from HuggingFaceH4/ultrachat_200k.

File size

	Size
BF16 source (`Qwen/Qwen3.5-0.8B`)	1.7 GB
This W8A8 model	1.4 GB

Notes / gotchas

vLLM ≥ 0.17 required (qwen3_5_mtp speculative method only landed there).
transformers ≥ 5.x is required for qwen3_5 model_type.
The MTP head weights are stored as mtp.* keys in the safetensors file; do not delete or re-quantize them. The companion quantization_config.ignore list explicitly excludes the 8 MTP Linear modules so vLLM treats them as float.
For multi-stream serving raise --max-model-len and --max-num-seqs to taste.

Reproducing

The quantization script is at https://huggingface.co/vadery/qwen36-27b-ft-grm-w8a8 (sibling 27B model), parameterized for the 0.8B's layer count.

License

Inherits Apache 2.0 from the base model.

Downloads last month: 48

Safetensors

Model size

0.9B params

Tensor type

BF16

Model tree for vadery/Qwen3.5-0.8B-W8A8

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(418)

this model