Instructions to use litert-community/Zamba2-2.7B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/Zamba2-2.7B-instruct 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=litert-community/Zamba2-2.7B-instruct \ --prompt="Write me a poem"
- LiteRT
How to use litert-community/Zamba2-2.7B-instruct 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
18 days ago
-
Card: one Engine per conversation on LiteRT-LM (own report #3165), measured on litert-lm 0.18.0
Verified signature04cacdd
-
Chat template: accept the 0.18 content-parts form (string form unchanged); weights, tokenizer and executor metadata byte-identical
Verified signature7e6e081
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature0fc6e8c
-
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature3310f6c
-
Add measured Raspberry Pi 5 (CPU) section
Verified signatureNumbers from the 2026-09 Raspberry Pi 5 LLM sweep: litert-lm benchmark 0.16.1, CPU backend, 4 threads, 256 prefill + 256 decode tokens, compile cache disabled, 3 invocations per file with cooldown, thermal throttle state verified 0x0 on every run, and a real-generation gate on the same backend before any number was recorded. Median + spread, never single-shot.97565fa
-
Card: correct the start_token note — measured numbers do not carry over
Verified signature695c6a5 -
Card: note the start_token fix (weights unchanged)
Verified signature7b41085 -
Drop the metadata start_token (weights unchanged)
Verified signatureThe engine prepends the metadata start_token to every prompt, and this template already renders the BOS itself, so the model was reading it twice. Metadata-only change: every tokenizer and TFLite section is byte-identical to the previous file (verified by sha256 per section), so quality and speed are unchanged and the card's measured numbers still stand.d5f2dc5
-
Add measured Galaxy S26 GPU backend section
Verified signatureFunctional verdict from the S26 GPU gate. Primary log: litertlm-convert/community_accel_work/s4_gpu_gate/results.jsonl. Delegation counts and peak RSS are read from that run's own log; throughput is deliberately absent, because an Android GPU speed is not quotable without a CPU row from the same phone and that control has not been run.aab72d6
-
Zamba2-2.7B int8 (fp32act, full prefill ladder)
Verified signaturebf050bb -
Zamba2-2.7B LiteRT-LM card
Verified signature436d4d1 -
initial commit
Verified signaturea4ae3e7