Ornith 1.0 (35B, Q8)
DeepReinforce's Ornith 1.0 at 35B parameters — an agentic-coding model built for hands-on software work: reading a codebase, running tools, and seeing a change through. Native reasoning, native tool calling, 256K context. 8-bit quantization for higher fidelity than the Q4 build, at roughly double the memory footprint (~37GB). MIT licensed.
| At a glance | |
|---|---|
| Made by | DeepReinforce |
| Download size | 37.0 GB |
| Parameters | 35B |
| Quantization | Q8_0 |
| Context window | 262K tokens |
| Uses tools | Yes |
| Best for | Coding |
| Runs on | llama.cpp, MLX |
| License | MIT |
| Added to the catalog | 2026-08-15 |
Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.