MoEDiet run artifacts

Run outputs of MoEDiet experiments: audited expert-pruning checkpoints, quantized GGUF exports, masks, and build reports, organized per job under runs/<JOB_ID>/ (source snapshots of each submitted job are kept under requests/<ID>/).

Weights are derivatives of Apache-2.0 models (AllenAI OLMoE-1B-7B-0125-Instruct, Qwen/Qwen3-Next-80B-A3B-Instruct) and are distributed under the same Apache-2.0 terms, with attribution to the original authors. Each run directory carries its own report.json with the exact source revision, routing, and quality audit.

Downloads last month
22
GGUF
Model size
7B params
Architecture
olmoe
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support