Ornith 1.0 9B
DeepReinforceDeepReinforce's open-weights agentic coding model, a 9B dense model built on the Qwen 3.5 architecture, with explicit <think> reasoning and tool-calling for terminal-based software-engineering tasks. Optimized for single-GPU deployment (~19GB in bf16).
MIT-licensed open weights (HF tag license:mit), Qwen 3.5 architecture (qwen3_5), released 2026 by DeepReinforce. ~64k downloads/mo on the primary weights repo plus ~288k/mo on the GGUF quant (~352k combined, July 2026); 361 / 407 likes. Reported coding benchmarks include SWE-Bench Verified 69.4, SWE-Bench Pro 42.9, and Terminal-Bench 2.1 ~43.
Openness
3 high confidence- weights
- open(MIT)
- base
- Qwen3.5
- data
- closed
- recipe
- closed
- license
- MIT(OSI)
MIT-licensed open weights on a Qwen 3.5 base, but no open training data or recipe -> open_weights.
- https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B recorded 2026-07-03
license:mit tag; qwen3_5 architecture; safetensors weights
Adoption
3 medium confidence~352k HF downloads last month combined across the primary weights repo (~64k) and the GGUF quant (~288k), July 2026; 361 + 407 likes. Squarely in the 100k-1M band.
- https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B recorded 2026-07-03
64,051 downloads last month, 361 likes
- https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B-GGUF recorded 2026-07-03
287,942 downloads last month, 407 likes
Capability
4 medium confidenceStrong agentic-coding scores for a 9B and competitive within the category, but below the frontier coders; benchmarks are vendor-reported on the model card.
- https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B recorded 2026-07-03
reported SWE-Bench Verified / Pro and Terminal-Bench results
Unchanged since 2026-07-03 (last edited, not re-checked)