The largest model in the Solus catalogue. Qwen2.5 14B Instruct is a broadly capable general model with strong multilingual coverage, solid coding and maths, and better long-form writing than anything smaller here.
It needs real hardware: budget around 16 GB of system RAM, or 10 GB of VRAM to run it comfortably on a GPU. On a machine that can host it, it is the best quality option in the catalogue. Apache 2.0 licensed.
Quantization performed at the Faculty of Engineering, McMaster University.
The GGUF conversion this build is derived from was produced by
bartowski, and the
weights here are a byte-for-byte copy of that file — the SHA-256 above matches
the upstream artifact.
