You can deploy this model and start earning money today!

drawais/
Qwen3-Embedding-4B-AWQ-INT4

Name: Qwen3-Embedding-4B-AWQ-INT4
Availability: InStock

Qwen/Qwen3-Embedding-4B

quantized

apache-2.0

text-generation-inference

endpoints_compatible

compressed-tensors

Views

No views yet

Qwen3-Embedding-4B-AWQ-INT4

INT4 weight-only quantization of Qwen/Qwen3-Embedding-4B.

Qwen 3 Embedding 4B in INT4. Drop-in for any embedding stack. Fits on a 6 GB consumer GPU.

Property	Value
Base model	Qwen/Qwen3-Embedding-4B
Quantization	INT4 weight-only
Approx. on-disk size	~2.7 GB
Languages	English

Load (vLLM)

bash

vllm serve drawais/Qwen3-Embedding-4B-AWQ-INT4 \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.94

python

from vllm import LLM, SamplingParams
llm = LLM(model="drawais/Qwen3-Embedding-4B-AWQ-INT4", max_model_len=32768)
print(llm.generate(["Hello!"], SamplingParams(max_tokens=128))[0].outputs[0].text)

Footprint

~2.7 GB on disk. Recommended VRAM: enough headroom for KV cache.

License & attribution

This artifact is a derivative work of Qwen/Qwen3-Embedding-4B, released by its original authors under the Apache License, Version 2.0.

This artifact is distributed under the same license. The full license text is included in LICENSE, and required attribution is in NOTICE.

License text: https://www.apache.org/licenses/LICENSE-2.0 Source model: https://huggingface.co/Qwen/Qwen3-Embedding-4B