# spark-control model catalog
#
# Edit this file (or override at runtime via the StartOS "Edit Model Catalog"
# action) to add or change available models.
#
# Each model entry produces this command on Spark 1:
#   cd ~/spark-vllm-docker
#   ./launch-cluster.sh [--solo] -d exec vllm serve <repo> \
#     --port=<defaults.port> --host=<defaults.host> <vllm_args...>

defaults:
  port: 8888
  host: 0.0.0.0

models:
  qwen3-vl:
    display_name: "Qwen3-VL 235B (vision)"
    description: >-
      Qwen's flagship multimodal model. 235B total parameters with ~22B
      active per token (Mixture-of-Experts). Handles text, images, and
      many languages. The most capable model in this catalog — also the
      slowest to load because it splits across both Sparks.
    repo: RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4
    size_gb: 135
    mode: cluster
    capabilities: [vision, multilingual]
    expected_ready_seconds: 300
    vllm_args:
      - --gpu-memory-utilization=0.7
      - -tp=2
      - --distributed-executor-backend=ray
      - --max-model-len=32768
      - --max-num-batched-tokens=16384

  gemma4:
    display_name: "Gemma 4 31B"
    description: >-
      Google's mid-size reasoning model. 31B dense parameters with built-in
      thinking mode and function-calling. Strong on math, logic, and
      structured outputs; also supports vision input. Runs solo on one Spark.
    repo: RedHatAI/gemma-4-31B-it-NVFP4
    size_gb: 23
    mode: solo
    capabilities: [vision, reasoning, tools]
    expected_ready_seconds: 240
    vllm_args:
      - --gpu-memory-utilization=0.8
      - --max-model-len=32768
      - --max-num-batched-tokens=16384
      - --reasoning-parser=gemma4
      - --tool-call-parser=gemma4
      - --enable-auto-tool-choice
      - --load-format=fastsafetensors
      - --enable-prefix-caching
      - --kv-cache-dtype=fp8

  qwen36:
    display_name: "Qwen3.6 35B-A3B (daily driver)"
    description: >-
      Qwen's latest fast Mixture-of-Experts model: 35B total parameters but
      only ~3B active per token, making inference quick. Long 64K-token
      context window. A good default for everyday chat and longer documents.
    repo: RedHatAI/Qwen3.6-35B-A3B-NVFP4
    size_gb: 20
    mode: solo
    capabilities: [reasoning]
    expected_ready_seconds: 300
    vllm_args:
      - --gpu-memory-utilization=0.85
      - --max-model-len=65536
      - --max-num-batched-tokens=16384
      - --reasoning-parser=qwen3
      - --moe_backend=flashinfer_cutlass
      - --load-format=fastsafetensors
      - --enable-prefix-caching
      - --kv-cache-dtype=fp8

  qwen3-235b-fp8:
    display_name: "Qwen3 235B-A22B FP8 (legacy)"
    description: >-
      Earlier generation of the Qwen 235B family in native FP8 precision.
      Runs across both Sparks. Mostly superseded by Qwen3-VL above; keep
      around for text-only baseline comparisons.
    repo: Qwen/Qwen3-235B-A22B-FP8
    size_gb: 220
    mode: cluster
    capabilities: []
    expected_ready_seconds: 360
    vllm_args:
      - --gpu-memory-utilization=0.7
      - -tp=2
      - --distributed-executor-backend=ray
      - --max-model-len=32768

  qwen25-72b:
    display_name: "Qwen2.5 72B (legacy)"
    description: >-
      Last-generation 72B dense model. Cluster mode required due to size.
      Kept for compatibility and baseline comparison against newer Qwens.
    repo: Qwen/Qwen2.5-72B-Instruct
    size_gb: 145
    mode: cluster
    capabilities: []
    expected_ready_seconds: 360
    vllm_args:
      - --gpu-memory-utilization=0.7
      - -tp=2
      - --distributed-executor-backend=ray
      - --max-model-len=32768