config/models.yaml

models:
  minicpm5_1b:
    hf_id: openbmb/MiniCPM5-1B
    display_name: MiniCPM5 1B
    type: text
    parameters_b: 1
    backend: transformers
    backend_capabilities:
      placeholder: [text]
      ollama: [text, streaming]
      llama.cpp: [text, gguf]
      llama-cpp-python: [text, gguf]
      transformers: [text, lora]
      openai-compatible: [text, openai-compatible]
      sglang: [text, tools]
      vllm: [text, openai-compatible]
    context_length: 131072
    local_first: true
    thinking_mode: false
    gguf:
      available: true
      repo: openbmb/MiniCPM5-1B-GGUF
      default_quant: Q4_K_M
    notes: Text baseline for local chat, LoRA experiments, and GGUF export.

  minicpm5_1b_thinking:
    hf_id: openbmb/MiniCPM5-1B-Thinking
    display_name: MiniCPM5 1B Thinking
    type: text
    parameters_b: 1
    backend: transformers
    backend_capabilities:
      placeholder: [text]
      ollama: [text, thinking, streaming]
      llama.cpp: [text, gguf]
      llama-cpp-python: [text, gguf]
      transformers: [text, thinking, lora]
      openai-compatible: [text, thinking, openai-compatible]
      sglang: [text, thinking, tools]
      vllm: [text, openai-compatible]
    context_length: 131072
    local_first: true
    thinking_mode: true
    gguf:
      available: true
      repo: openbmb/MiniCPM5-1B-Thinking-GGUF
      default_quant: Q4_K_M
    notes: Thinking variant for explicit reasoning experiments.

  minicpm41_8b:
    hf_id: openbmb/MiniCPM4.1-8B
    display_name: MiniCPM4.1 8B
    type: text
    parameters_b: 8
    backend: transformers
    backend_capabilities:
      placeholder: [text]
      ollama: [text, streaming]
      llama.cpp: [text, gguf]
      llama-cpp-python: [text, gguf]
      transformers: [text, long-context]
      openai-compatible: [text, long-context, openai-compatible]
      sglang: [text, long-context, tools]
      vllm: [text, long-context, openai-compatible]
    context_length: 131072
    local_first: true
    thinking_mode: false
    trust_remote_code: true
    gguf:
      available: true
      repo: openbmb/MiniCPM4.1-8B-GGUF
      default_quant: Q4_K_M
    notes: Long-context sparse-attention text model; real backend will require trust_remote_code.

  nemotron_nano_9b_v2:
    hf_id: nvidia/NVIDIA-Nemotron-Nano-9B-v2
    display_name: NVIDIA Nemotron Nano 9B v2
    type: text
    parameters_b: 9
    backend: transformers
    backend_capabilities:
      placeholder: [text]
      llama.cpp: [text, gguf]
      llama-cpp-python: [text, gguf]
      transformers: [text, custom-code]
      openai-compatible: [text, openai-compatible]
      sglang: [text]
      vllm: [text, openai-compatible]
    context_length: 131072
    local_first: true
    thinking_mode: false
    trust_remote_code: true
    gguf:
      available: true
      repo: bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF
      default_quant: Q4_K_M
    notes: Small Nemotron text option under the 32B hackathon limit; verify license and hardware before using in a public Space.

  minicpm_v46:
    hf_id: openbmb/MiniCPM-V-4.6
    display_name: MiniCPM-V 4.6
    type: vision
    parameters_b: 1.3
    backend: transformers
    backend_capabilities:
      placeholder: [vision]
      ollama: [vision]
      llama.cpp: [vision, gguf, mmproj]
      transformers: [vision, image-text-to-text]
      sglang: [vision, openai-compatible]
    context_length: 262144
    local_first: true
    thinking_mode: false
    gguf:
      available: true
      repo: openbmb/MiniCPM-V-4.6-gguf
      main_file: MiniCPM-V-4.6-Q4_K_M.gguf
      mmproj: mmproj-MiniCPM-V-4.6-F16.gguf
      default_quant: Q4_K_M
    notes: Vision-language model candidate for image and video understanding.

  minicpm_v46_thinking:
    hf_id: openbmb/MiniCPM-V-4.6-Thinking
    display_name: MiniCPM-V 4.6 Thinking
    type: vision
    parameters_b: 1.3
    backend: transformers
    backend_capabilities:
      placeholder: [vision, thinking]
      ollama: [vision, thinking]
      llama.cpp: [vision, gguf, mmproj]
      transformers: [vision, thinking, image-text-to-text]
      sglang: [vision, thinking, openai-compatible]
    context_length: 262144
    local_first: true
    thinking_mode: true
    gguf:
      available: true
      repo: openbmb/MiniCPM-V-4.6-Thinking-gguf
      default_quant: Q4_K_M
    notes: Vision-language thinking variant for multimodal reasoning demos.

  minicpm_o45:
    hf_id: openbmb/MiniCPM-o-4.5
    display_name: MiniCPM-o 4.5
    type: omnimodal
    parameters_b: 8
    backend: transformers
    backend_capabilities:
      placeholder: [text, vision, audio]
      transformers: [text, vision, audio]
    context_length: 131072
    local_first: true
    thinking_mode: false
    notes: Omnimodal stretch goal for audio, image, and text.