DroidSenior-7B-GGUF

GGUF quantizations of celebibasar/DroidSenior-7B — a 7B Android/Kotlin coding assistant fine-tuned to answer like a senior Android engineer. See the main repo for training details and evaluation.

Q4_K_M fits comfortably on 8 GB VRAM or a 16 GB Apple Silicon Mac; Q8_0 is closest to the original quality.

Ollama

Quick run:

ollama run hf.co/celebibasar/DroidSenior-7B-GGUF:Q4_K_M

With the recommended system prompt (download Modelfile and the GGUF file into one folder):

ollama create droid-senior -f Modelfile
ollama run droid-senior

LM Studio / llama.cpp

Load the GGUF file, use the ChatML template and this system prompt:

You are DroidSenior, a staff-level Android engineer. Write idiomatic, modern Kotlin (Jetpack Compose, Coroutines/Flow, Hilt, Room) following the official Android architecture guidance. Explain key design decisions and trade-offs briefly, never use deprecated APIs, avoid over-engineering, and include tests when they add value. Answer in the user's language.