Modelpublic

drawais/Phi-4-mini-instruct-AWQ-INT4

sourceHugging Facemitupdated 5mo agoView on Hugging Face

0likes776downloads

Model Card

Phi-4-mini-instruct-AWQ-INT4

INT4 weight-only quantization of `microsoft/Phi-4-mini-instruct`.

Microsoft Phi-4-mini-instruct in INT4. About 2.5 GB on disk. Runs on a 4 GB consumer GPU.

Property	Value
Base model	microsoft/Phi-4-mini-instruct
Quantization	INT4 weight-only
Approx. on-disk size	~2.9 GB
License	MIT License
Languages	English

Load (vLLM)

bash

vllm serve drawais/Phi-4-mini-instruct-AWQ-INT4 \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.94

python

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

Footprint

~2.9 GB on disk. Recommended VRAM: enough headroom for KV cache.

License & attribution

This artifact is a derivative work of `microsoft/Phi-4-mini-instruct`, released by its original authors under the MIT License.

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://opensource.org/license/mit Source model: https://huggingface.co/microsoft/Phi-4-mini-instruct