Instructions to use mlboydaisuke/MiniCPM5-2B-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use mlboydaisuke/MiniCPM5-2B-LiteRT with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=mlboydaisuke/MiniCPM5-2B-LiteRT \ --prompt="Write me a poem"
- LiteRT
How to use mlboydaisuke/MiniCPM5-2B-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
Yesterday
-
Card: GPU executor defaults note — the 2026-10-13 re-pack changed llm_model_type, and with it the runtime's GPU defaults; the phone GPU rows were measured with the previous files
Verified signature1c2da3f -
litertlm_manifest.json: known_issues gain the GPU executor defaults sentence for MiniCPM5-2B_int4.litertlm and _int8.litertlm (the 2026-10-13 re-pack changed llm_model_type, and with it the runtime's GPU defaults; the phone GPU rows were measured with the previous files)
Verified signatureacc9e68 -
Card: the 2026-10-13 re-pack with the official LiteRT-LM minicpm5 config (tools work; requires litert-lm >= 0.18.0; direct answers by default)
Verified signature5829182 -
litertlm_manifest.json: the 2026-10-13 re-packed files (sha256, size, sections), their tool-call known_issues line and runtime floor
Verified signatured84969d -
Re-pack MiniCPM5-2B_int8.litertlm: official LiteRT-LM minicpm5 config (metadata only; tool calls parse on litert-lm 0.18.0, which this file now requires)
Verified signaturecb9a20c -
Re-pack MiniCPM5-2B_int4.litertlm: official LiteRT-LM minicpm5 config (metadata only; tool calls parse on litert-lm 0.18.0, which this file now requires)
Verified signature967ffe1
7 days ago
-
manifest 0.1.3: capabilities.thinking.control = switch (what the bundle's template does about thinking, derived from the template inside the bundle)
Verified signaturefc93c93
23 days ago
-
Chat template: accept the 0.18 content-parts form (string form unchanged); weights, tokenizer and executor metadata byte-identical
Verified signature013a833
-
Add litertlm_manifest.json (measured rows, verified backends, known issues)
Verified signature02e8a86 -
MiniCPM5-2B int8 (dynamic, linears + embedding; fp32 activations declared; verbatim jinja + thought channel)
Verified signature227079e -
MiniCPM5-2B int4 (blockwise-32 + OCTAV linears, int8 embedding; zero-scale fix; verbatim jinja + thought channel)
Verified signaturee2abce3 -
MiniCPM5-2B LiteRT-LM card
Verified signature5865490 -
initial commit
Verified signature5c4bdb0