# 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; the
# resulting `(catalogue × topology)` set is what `GET /v1/models`
# returns and what the router can cold-load on demand.
#
# Field reference:
#   id                 - HuggingFace model id, exact match.
#   harness            - which engine handles inference (currently "candle").
#   quant              - GGUF quantisation tag for the file in the HF repo
#                        (e.g. "Q4_K_M"). Omit/empty for the dense
#                        safetensors path. TP requires dense.
#   vram_mb            - rough estimate; advisory only, not enforced.
#   min_devices        - GPU count this profile needs. TP profiles use
#                        the same value as the tensor-parallel size.
#   min_device_vram_mb - each device must meet this VRAM floor for the
#                        neuron to be considered "feasible".
#   pinned_on          - optional whitelist of neuron names. Non-empty
#                        narrows feasibility to just those neurons and
#                        protects the model from LRU eviction there.

# Tensor-parallel target — needs a neuron with at least 2 large GPUs.
# The example pins to a specific neuron name; adjust or remove the
# pinned_on entry for your own fleet.
[[models]]
id = "Qwen/Qwen3.6-27B"
harness = "candle"
vram_mb = 54000
min_devices = 2
min_device_vram_mb = 24000
pinned_on = ["your-multi-gpu-neuron"]

# Mid-size dense model — fits on any single GPU with ≥16 GB VRAM.
[[models]]
id = "Qwen/Qwen3-8B"
harness = "candle"
vram_mb = 18000
min_devices = 1
min_device_vram_mb = 16000

# Small GGUF quantised — runs on any small GPU.
[[models]]
id = "unsloth/Qwen3-0.6B-GGUF"
harness = "candle"
quant = "Q4_K_M"
vram_mb = 500
min_devices = 1
min_device_vram_mb = 4000