# models.example.toml — model catalogue
#
# Copy to /etc/cortex/models.toml and adjust for your environment.
# Describes how to serve each model. Cortex matches these profiles
# against discovered neuron topologies for placement decisions.

[[models]]
id = "your-org/large-model"
harness = "candle"
quant = "Q4_K_M"
vram_mb = 19000
min_devices = 2
min_device_vram_mb = 10000
pinned_on = ["gpu-large"]

[[models]]
id = "your-org/medium-model"
harness = "candle"
quant = "Q6_K"
vram_mb = 12000
min_devices = 1
pinned_on = ["gpu-medium"]

[[models]]
id = "your-org/embedding-model"
harness = "candle"
quant = "Q8_0"
vram_mb = 8000
min_devices = 1