Darkbloom
Decentralised private inference network running open models on contributed Apple Silicon Macs, via an OpenAI-compatible API.
Overview
Darkbloom models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- Gemma 4 26B A4B google/gemma-4-26b-a4b-itView model: Gemma 4 26B A4B
- Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningView model: Nemotron 3.5 Lightning
- Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vlView model: Nemotron 3.5 Super VL
- gpt-oss-20bopenai/gpt-oss-20bView model: gpt-oss-20b
- Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27bView model: Ternary Bonsai 2 27B
- Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9bView model: Ternary Bonsai 2 9B
- Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bView model: Qwen3.5-35B-A3B
- Qwen3.5-9Bqwen/qwen3.5-9bView model: Qwen3.5-9B
- Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bView model: Qwen3.6 35B A3B
- Qwen3.8 27Bqwen/qwen3.8-27bView model: Qwen3.8 27B
- MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashView model: MiMo-V2.6-Flash
- GLM 5.3 Flashz-ai/glm-5.3-flashView model: GLM 5.3 Flash
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Darkbloom models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.