No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from drawais/Phi-4-mini-instruct-AWQ-INT4
All models by drawais →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.
~2.9 GB on disk. Recommended VRAM: enough headroom for KV cache.
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 [blocked], and required attribution is in NOTICE [blocked].
License text: https://opensource.org/license/mit Source model: https://huggingface.co/microsoft/Phi-4-mini-instruct
vllm serve drawais/Phi-4-mini-instruct-AWQ-INT4 \ --max-model-len 32768 \ --gpu-memory-utilization 0.94from vllm import LLM, SamplingParamsllm = 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)