The model is converted from the original LocoreMind/LocoOperator-4B using:

litert-torch export_hf \
    --model=LocoreMind/LocoOperator-4B \
    --output_dir="./dynamic_wi8_afp32" \
    --quantization_recipe="dynamic_wi8_afp32" \
    --bundle_litert_lm=true

Downloads last month: 40

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for 4ntoine/LocoOperator-4B-LiteRTLM

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

LocoreMind/LocoOperator-4B

Finetuned

(1)

this model