Skip to content

nimble:9b-v3

4 TagsUpdated 9B params32768 contextEnglishApache-2.0by Bespoke Labs

Bespoke-Nimble-9B v3: v2's prompts with a new LoRA, served as the author's Decision Index engine. CC BY-NC 4.0 (non-commercial). Needs a 24 GB GPU.

9b
ollaya run nimble:9b-v3 --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph580684d57571 · 14 MBonnx · nimble · 9B · fp32
  • weightsdb6f444b43d3 · 5.3 GBhuggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00001-of-00004.safetensors
  • weights31c7d7e2dd5d · 5.3 GBhuggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00002-of-00004.safetensors
  • weights7ec36ba3a417 · 5.4 GBhuggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00003-of-00004.safetensors
  • weightsb62b0c4cd7e4 · 3.3 GBhuggingface.co/Qwen/Qwen3.5-9B/resolve/c202236…/model.safetensors-00004-of-00004.safetensors
  • weights070d80aca59a · 693 MBhuggingface.co/bespokelabs/Bespoke-Nimble-9B-v3/resolve/8e927b9…/adapter_model.safetensors
  • tokenizer06b9509352d2 · 20 MBhuggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/tokenizer.json
  • decision8bb050a8b4da · 11 KB{"engine": "onnx", "family": "nimble", "encoder": "", "layout": "nimble-codes-v1", …}
  • calibrationb81368429eca · 198 B{"temperature": [1.0, 1.0, 1.0]}
  • licenseaf2c038d093c · 11 KBBespoke-Nimble-9B-v3 by Bespoke Labs (https://huggingface.co/bespokelabs/Bespoke-Nimble-9B-v3)

Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.

Nimble readme and all models