This repository contains Geer's independently produced 6-bit MLX conversion
of
Deep Reinforce AI's Ornith-1.0-35B. It is intended for local
agentic coding on Apple Silicon through
Geer.
The model identity is intentionally transparent: this is Ornith-1.0-35B,
converted by the Geer project. It is not a new foundation model.
The reproducible conversion tool and tensor-layout transformation are
available in the
Geer source repository.
Geer downloads this repository at an immutable revision, verifies every file
against geer-build-manifest.json, and activates the verified Hugging Face
snapshot without copying the model into another directory.
See the
Geer README for the current T3 Code and Claude Code proof of
concept. Geer 0.1.0 selects this conversion on Macs with 64 GB or more of
unified memory and configures a 256K context window with BF16 KV cache.
Deep Reinforce AI publishes results for the upstream BF16 Ornith model in its
model card. Geer has verified that this conversion loads and works
through its local MLX serving pipeline. Geer has not yet reproduced the
upstream benchmark suite for this quantization, so upstream scores should not
be treated as measured results for this conversion. Although the upstream
architecture and repository metadata support image-and-text inputs, Geer 0.1.0
has validated this conversion only for text-based agentic coding workflows.
Deep Reinforce AI declares Ornith-1.0-35B under the MIT license. Its model card
states that Ornith-1.0-35B was post-trained on Qwen 3.5; the applicable Qwen
Apache License 2.0 text and attribution are preserved here. See LICENSE,
LICENSE-QWEN, and NOTICE before using or redistributing the model.
Geer is an independent project and is not affiliated with or endorsed by Deep
Reinforce AI or Alibaba Cloud.
