Hugging Face's logo

shuttleai
/
shuttle-3.5-awq

Safetensors
qwen3
4-bit precision
awq
Model card Files Community
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Base: shuttleai/shuttle-3.5
Model: 4-bit quantized AWQ model
Format: AWQ (AutoAWQForCausalLM)
Bit: 4
Group Size: 128
Zero Point: True
Version: GEMM
Source: Fine-tuned with LoRA, then merged and quantized
Downloads last month
48
Safetensors
Model size
5.73B params
Tensor type
I32
·
BF16
·
FP16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including shuttleai/shuttle-3.5-awq