ThoxNeedle-Micro
THOX-branded on-device model derived from Cactus-Compute/needle2, fine-tuned on the THOX chat + agent/tool-use corpora and quantized for the ThoxKey tier. Status: skeleton โ weights pending fine-tune + quantize.
Intended use
On-device assistant / tool-routing for the THOX device program.
Out of scope
Not for safety-critical, medical, or legal decisions without a human in the loop.
Provenance & license
Base: Cactus-Compute/needle2 (apache-2.0).
Quantization (to be filled by measured bench)
| Quant | On-disk | RAM/RSS | tok/s CPU |
|---|---|---|---|
| Q4_K_M | TBD | TBD | TBD |
Decensor policy for this repo: public.
Model tree for Thox-ai/ThoxNeedle-Micro
Base model
Cactus-Compute/needle2