Pyyan / Open-Weight Models / Edge0-145B

E

Edge0-145B

A 145B model with about 10B active per token that Edge0 says runs in 29GB on a laptop.

currentEdge0 ↗Verified 2026-11-13

145B

total, about 10B active

Specifications

Context256Ksource · as of 2026-11-13
Input ($/Mtok)Weights onlysource · as of 2026-11-13
Output ($/Mtok)Weights onlysource · as of 2026-11-13
LicenceEdge0 Community Model License 1.0 (Qwen terms apply)source · as of 2026-11-13
Max outputNot publishedsource · as of 2026-11-13
Parameters145B total, about 10B activesource · as of 2026-11-13
Released12 Nov 2026source · as of 2026-11-13
Model IDEdge0/Edge0-145B-q3ksource · as of 2026-11-13

What matters

  • Weights on Hugging Face in Q3_K (40.81 GiB) and NVFP4 (47.79 GiB) builds, with Edge0-120B alongside
  • Edge0 reports 29GB peak memory, over 80 tokens a second and 86.52 on Terminal-Bench 2.1. These are its own figures, and its technical report is not yet out
  • The Hugging Face build instructions target NVIDIA CUDA 13. Edge0's blog claims day-one macOS support, while the card says its Apple measurements do not establish macOS availability
  • Licence is Edge0 Community Model License 1.0 for Edge0's contributions, with Qwen Community License terms still applying to Qwen materials
  • Selling the model, running a commercial model service or shipping a paid coding or office assistant on it needs a separate written licence from Edge0

Best for trying a large coding model locally on a 48GB laptop or a single 24GB GPU with host RAM.