You can deploy this model and start earning money today!

drawais/
Phi-4-reasoning-AWQ-INT4

Name: Phi-4-reasoning-AWQ-INT4
Availability: InStock

microsoft/Phi-4-reasoning

quantized

mit

text-generation-inference

endpoints_compatible

compressed-tensors

Views

No views yet

Phi-4-reasoning-AWQ-INT4

INT4 weight-only quantization of microsoft/Phi-4-reasoning.

Microsoft Phi-4-reasoning in INT4. About 7 GB on disk. Reasoning model, fits a single 16 GB consumer GPU.

Property	Value
Base model	microsoft/Phi-4-reasoning
Quantization	INT4 weight-only
Approx. on-disk size	~9.1 GB
License	MIT License
Languages	English

Load (vLLM)

bash

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

python

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

Footprint

~9.1 GB on disk. Recommended VRAM: enough headroom for KV cache.

License & attribution

This artifact is a derivative work of microsoft/Phi-4-reasoning, 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-reasoning