MiniCPM5: SOTA on-device LLMs, small yet powerful.
MiniCPM is a family of compact language models, including MiniCPM5-1B, designed to run locally on devices with limited resources. Developers use it for on-device assistants, reasoning, code, tool use, deployment, and fine-tuning, while the repository also includes a desktop-pet example. The catalogue entries support deployment and fine-tuning workflows for the models.
Skill Claude CodeCodex needs its repo
ArcLight is a lightweight C/C++ LLM inference framework for unified-memory systems. The recommended path is to build from source, then run a GGUF model with al-gen, al-chat, or al-ppl.
Skill Claude CodeCodex
Run MiniCPM5-1B or MiniCPM5-2B with llama.cpp using the released GGUF artifacts (F16 / Q80 / Q4KM). Use when the user wants CPU-only / consumer-GPU / cross-platform native deployment, asks for "llama.cpp", "llama-cli", "llama-server", "GGUF", or has no Python available.
Skill Claude CodeCodex
Run MiniCPM5-1B or MiniCPM5-2B in LM Studio (desktop GUI) using either the GGUF runtime (cross-platform) or the MLX runtime (Apple Silicon, faster). Includes OpenAI-compatible local server. Use when the user mentions "LM Studio", desktop GUI inference, "lms" CLI, or wants a no-code chat UI for MiniCPM5.
Skill Claude CodeCodex
Run MiniCPM5-1B or MiniCPM5-2B natively on Apple Silicon with Apple's MLX framework. Use when the user has an Apple Silicon Mac and asks for "MLX", "mlxlm", "mlxlm.convert", "mlxlm.generate", or wants the fastest path on Apple Silicon.
Skill Claude CodeCodex
Run MiniCPM5-1B or MiniCPM5-2B via Ollama on macOS / Linux laptop using the released GGUF. Use when the user wants "ollama run", "ollama pull", a Modelfile-driven setup, or one-line laptop deployment.
Skill Claude CodeCodex
Serve MiniCPM5-1B or MiniCPM5-2B via SGLang as an OpenAI-compatible HTTP server with RadixAttention prefix cache and built-in MiniCPM5 tool-call parsing. Use when the user asks for "SGLang", "RadixAttention", "prefix cache", batch evaluation, tool calling, or wants a high-concurrency NVIDIA-GPU server alternative to…
Skill Claude CodeCodex
Run MiniCPM5-1B or MiniCPM5-2B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.
Skill Claude CodeCodex
Serve MiniCPM5-1B or MiniCPM5-2B via vLLM as an OpenAI-compatible HTTP server. Use when the user wants high-throughput production serving on NVIDIA GPU, asks for "vLLM", "OpenAI server", "REST API for MiniCPM5", or "production deployment".
Skill Claude CodeCodex
Pick the right inference backend for a MiniCPM5-1B or MiniCPM5-2B checkpoint and route to a backend-specific cookbook skill. Use when the user wants to deploy / serve / chat-with / benchmark a MiniCPM5 model and has not yet committed to a specific engine, or when they say "deploy MiniCPM5", "run MiniCPM5", "serve…
Skill Claude CodeCodex
A workflow for fine-tuning MiniCPM5-1B and converting the result into a GGUF LoRA adapter. GGUF is a model file format used by tools such as llama.cpp, llama-server, and some desktop apps.
Skill Claude CodeCodex
Fine-tune MiniCPM5-1B or MiniCPM5-2B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI). Use when the user wants to fine-tune via LLaMA-Factory, llamafactory-cli, mentions YAML configs, WebUI, or asks for the most-documented community framework.
Skill Claude CodeCodex
Fine-tune MiniCPM5-1B or MiniCPM5-2B with ms-swift or Megatron-SWIFT. Use when the user mentions "ms-swift", "swift sft", "swift rlhf", or "megatron sft". MiniCPM5-1B uses the PyPI release with --template minicpm5; MiniCPM5-2B requires ms-swift>=4.6.0.dev0 with --template minicpm52b. Both use --modeltype llama.
Skill Claude CodeCodex
Fine-tune MiniCPM5-1B or MiniCPM5-2B with bare-metal TRL + PEFT, including assistant-only loss via a chat-template patch. Use when the user wants minimal Python, no YAML, full control, or asks for "TRL", "SFTTrainer", "PEFT", "LoraConfig", "assistantonlyloss".
Skill Claude CodeCodex
Fine-tune MiniCPM5-1B or MiniCPM5-2B with unsloth for tight-VRAM single-GPU LoRA / QLoRA. Use when the user wants "unsloth", "FastLanguageModel", QLoRA on a 24 GB consumer GPU, or asks for the smallest VRAM footprint.
Skill Claude CodeCodex
Fine-tune MiniCPM5-1B with xtuner (mmengine config-driven SFT). Use when the user mentions "xtuner", "mmengine", InternLM's training framework, or wants config-file-driven training.
Skill Claude CodeCodex
Pick the right fine-tuning framework for a MiniCPM5-1B base checkpoint and route to a framework-specific cookbook skill. Use when the user wants to SFT / LoRA / DPO / continue-pretrain MiniCPM5 and has not yet committed to a specific framework, or when they say "fine-tune MiniCPM5", "train MiniCPM5", "MiniCPM5 微调"…
Skill Claude CodeCodex
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
Skill Claude CodeCodex
Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says "LiteRT", "LiteRT-LM", "litertlm", ".litertlm", "Android"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: