Views
No views yet
ibm-granite/granite-4.1-8b.| Property | Value |
|---|---|
| Base model | ibm-granite/granite-4.1-8b |
| Quantization | INT4 weight-only |
| Approx. on-disk size | ~4.9 GB |
| Languages | English |
1vllm serve drawais/Granite-4.1-8B-AWQ-INT4 \
2 --max-model-len 32768 \
3 --gpu-memory-utilization 0.941from vllm import LLM, SamplingParams
2llm = LLM(model="drawais/Granite-4.1-8B-AWQ-INT4", max_model_len=32768)
3print(llm.generate(["Hello!"], SamplingParams(max_tokens=128))[0].outputs[0].text)ibm-granite/granite-4.1-8b,
released by its original authors under the Apache License, Version 2.0.LICENSE, and required attribution is in NOTICE.