Skip to content

jeb:4b

4 TagsUpdated 4B params4096 contextEnglishApache-2.0by frontier-infra

Jebadiah 4B v2, Q8_0 GGUF: the smallest and fastest Jeb.

4b
ollaya run jeb:4b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • weights36f4a54fe07e · 4.6 GBgguf · Q8_0 · huggingface.co/frontier-infra/jebadiah-4b-v2-GGUF/resolve/7f671f9…/jebadiah-4b-v2-Q8_0.gguf
  • decisionb13dec7accf8 · 7 KB{"engine": "llama", "family": "jebadiah", "layout": "jebadiah-v1", "gguf": {…}, …}
  • calibration421a8888666d · 163 B{"temperature": [1.117, 0.831, 1.332]}
  • licensebf69a57a4975 · 10 KBJebadiah by Jason Brashear and AINode (https://huggingface.co/frontier-infra, https://github.com/getainode/jebadiah): rank-16 LoRA merges into Qwen3.5-4B, Qwen3.5-9B and Qwen3.8-27B by the Qwen team (Apache-2.0), published by the authors as GGUF.

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.

Jebadiah readme and all models