This is an AWQ W4A16 (4-bit weight) quantized version of Qwen/Qwen3.5-9B, packaged in the compressed-tensors format for efficient inference with vLLM.

The quantization reduces the on-disk and VRAM footprint while preserving the base model's vision-language capabilities, making it well-suited to a single consumer GPU (e.g. an RTX 5090 / Blackwell, sm_120).

About the base model

Qwen3.5-9B is a multimodal vision-language model from the Qwen team (Alibaba Group). It accepts interleaved image + text (and video) input and generates text, with a "thinking" reasoning mode enabled by default.


Base model	Qwen/Qwen3.5-9B
Parameters	~9B
Modality	Image-Text-to-Text (vision-language)
Architecture	Hybrid Gated DeltaNet + sparse MoE, with a vision encoder
Context length	262,144 tokens native (extensible with RoPE scaling)
Languages	201 languages and dialects
License	Apache 2.0

For full details on capabilities, benchmarks, and prompt formatting, see the base model card.

Quantization details


Method	AWQ (Activation-aware Weight Quantization)
Scheme	W4A16 (4-bit weights, 16-bit activations)
Format	`compressed-tensors` (`pack-quantized`)
Quantized modules	Linear layers of the language model
Kept in higher precision	Vision tower, router gates, and `lm_head`

The vision tower is intentionally left unquantized to preserve image understanding quality.

Usage

Serve with vLLM (OpenAI-compatible API)

bash

docker run --rm --gpus all -p 8000:8000 \
  -v "$PWD:/models" \
  vllm/vllm-openai:latest \
  --model /models/Qwen3.5-9B-AWQ \
  --served-model-name Qwen3.5-9B-AWQ \
  --quantization compressed-tensors \
  --dtype float16 \
  --max-model-len 32768

Or directly from the Hub:

bash

docker run --rm --gpus all -p 8000:8000 \
  vllm/vllm-openai:latest \
  --model sanskar003/Qwen3.5-9B-AWQ \
  --quantization compressed-tensors \
  --dtype float16

Query it (text)

bash

curl -s http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' -d '{
    "model": "Qwen3.5-9B-AWQ",
    "messages": [{"role": "user", "content": "Give me three uses for an RTX 5090."}]
  }'

Query it (image + text)

bash

curl -s http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' -d '{
    "model": "Qwen3.5-9B-AWQ",
    "messages": [{"role": "user", "content": [
      {"type": "text", "text": "Describe this image."},
      {"type": "image_url", "image_url": {"url": "http://images.cocodataset.org/train2017/000000231895.jpg"}}
    ]}]
  }'

Requirements

A GPU with INT4 Marlin kernel support (vLLM selects it automatically for compressed-tensors checkpoints). Verified on NVIDIA Blackwell (sm_120).
A recent vLLM build that supports the Qwen3_5ForConditionalGeneration architecture.

License

Released under Apache 2.0, inherited from the base model Qwen/Qwen3.5-9B. Please review and comply with the base model's license terms.

Citation

Please cite the original Qwen work — see the base model card for citation details.