AI Potluck
Model components / Fine-tuned / chat models

Ornith 1.0 9B

DeepReinforce

DeepReinforce'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
3.0
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.

Adoption

3 medium confidence
3.0

~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.

Capability

4 medium confidence
4.0

Strong agentic-coding scores for a 9B and competitive within the category, but below the frontier coders; benchmarks are vendor-reported on the model card.

Unchanged since 2026-07-03 (last edited, not re-checked)