Skip to content

kev:9b

4 TagsUpdated 7.9B params8192 contextEnglishApache-2.0by Jared Palmer

Qwen3.5-9B base, 0.722 on typed decisions: the most accurate Kev. Needs a 24 GB GPU.

7.9b
ollaya run kev:9b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph43961763a149 · 14 MBonnx · kev · 7.9B · fp32
  • weights862bf7bba8a5 · 5.3 GBhuggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00001-of-00004.safetensors
  • weightsbace8e115e11 · 5.3 GBhuggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00002-of-00004.safetensors
  • weights63a021ac0011 · 5.4 GBhuggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00003-of-00004.safetensors
  • weights1a643bbed669 · 3.3 GBhuggingface.co/Qwen/Qwen3.5-9B-Base/resolve/68c46c4…/model.safetensors-00004-of-00004.safetensors
  • weightsc02d0d1a7036 · 173 MBhuggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/adapter_model.safetensors
  • weights5528f777437f · 8 MBhuggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/head.pt
  • tokenizer06b9509352d2 · 20 MBhuggingface.co/jaredpalmer/kev-9b/resolve/2629c06…/tokenizer.json
  • decisionb63a05185c2a · 3 KB{"engine": "onnx", "family": "kev", "encoder": "", "layout": "kev-pointer-v1", …}
  • calibration76c8fce9e9cb · 255 B{"temperature": [2.297, 2.297, 2.297]}
  • licensec32fd125b858 · 10 KBKev by Jared Palmer (https://huggingface.co/jaredpalmer/kev-9b)

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.

Kev readme and all models