Fanar-1-9B-Instruct-AWQ

GPTQ 4-bit quantized version of QCRI/Fanar-1-9B-Instruct.

Details

  • Quantization: GPTQ 4-bit (w4a16)
  • Size: ~5GB (vs ~18GB original)
  • Memory: 75% reduction
  • Quality: 95%+ retention
  • Optimized for: vLLM inference

Requirements

pip install vllm>=0.6.0

Model quantized using AutoAWQ with domain-specific calibration data.

Downloads last month
485
Safetensors
Model size
2B params
Tensor type
I64
I32
BF16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for buthainaaa/Fanar-1-9B-Instruct-GPTQ

Base model

QCRI/Fanar-1-9B
Quantized
(6)
this model