# neuron.toml for quadbrat.hanzalova.internal
#
# 1x RTX 3060 (12 GB) — small / quantised tier. Pre-warms Qwen3-1.7B
# (bf16, ~4 GB), leaving ~7 GB for KV cache so long contexts on a small
# model still have plenty of room.
#
# Synced by script/deploy.sh from asset/neuron/<short-host>.toml.

port = 13131

[[harnesses]]
name = "candle"

[harness.candle]

[[default_models]]
model_id = "Qwen/Qwen3-1.7B"
harness = "candle"
devices = [0]