# neuron.toml for benjy.hanzalova.internal
#
# 1x RTX 4090 (24 GB) — largest single-GPU host on the fleet. Pre-warms
# Qwen3-8B (bf16, ~18 GB), leaving ~6 GB for KV cache + activations on
# moderate-length contexts.
#
# Synced by script/deploy.sh from asset/neuron/<short-host>.toml.

port = 13131

[[harnesses]]
name = "candle"

[harness.candle]

[[default_models]]
model_id = "Qwen/Qwen3-8B"
harness = "candle"
devices = [0]