PEFT
Safetensors

Nimble V3

Nimble V3 is a LoRA adapter for Qwen/Qwen3.5-9B, made by Bespoke Labs. Given a context and typed questions (a choice among options, or yes or no), it returns a probability for each option.

Decision Index 0.2.1: 56.88. The full run, the inference code and instructions are in bespokelabs/nimble-v3-decision-index.

License

Nimble V3 is released under CC BY-NC 4.0, so it may not be used for commercial purposes. The base model, Qwen/Qwen3.5-9B, is licensed separately under Apache 2.0.

Citation

@misc{bespokelabs2026nimblev3,
  title        = {Nimble V3},
  author       = {Shreyas Pimpalgaonkar and Sid Devic and Mrinal Kumar and Pratik Dalal and Mahesh Sathiamoorthy},
  year         = {2026},
  publisher    = {Bespoke Labs},
  howpublished = {\url{https://huggingface.co/bespokelabs/Nimble-V3}}
}
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bespokelabs/Nimble-V3

Finetuned
Qwen/Qwen3.5-9B
Adapter
(740)
this model