Gemma 3 270M
A small language model with 270 million parameters released by Google as part of the Gemma 3 series, suited to deployment on edge devices.
Timeline (last 90 days)
Campaign Guard runs Gemma 3 270M locally via Ollama, feeding the saved promotional content along with its source information into the model, which returns a structured review result containing a summary, potential issues, and suggested edits.
Gemma 3 270M is a lightweight open model released by Google with only 270 million parameters, designed specifically for on-device and local inference, and it can be quickly loaded and run via Ollama on ordinary consumer hardware without sending data to the cloud.
Setting ort.wasm.wasmPaths to point to the regular WebAssembly build before loading any model allows 4-bit Gemma 3 270M (about 323 MB) to successfully load and run on Chrome's CPU.
This bug was exposed by an app named Paste-Safe, which locally in the browser masks customer names before the user pastes text into a chat AI, and uses Gemma 3 270M for an optional second check.
Candidate small models include SmolLM2 (135M and 360M), Gemma 3 270M, LFM2.5-350M, Qwen2.5-0.5B, and Qwen3-0.6B, all of which have ONNX browser builds.
In an evaluation of 30 answerable questions, off-the-shelf small models under 350MB achieved faithfulness (all assertions can be found in the passages) at most 3 times.
Zero-shot Gemma 3 270M is nearly unusable on the grammar correction task, with an F0.5 of only 0.122, and 99.6% of correct sentences were altered.
All Facts (6)
Campaign Guard runs Gemma 3 270M locally via Ollama, feeding the saved promotional content along with its source information into the model, which returns a structured review result containing a summary, potential issues, and suggested edits.
50%UnverifiedGemma 3 270M is a lightweight open model released by Google with only 270 million parameters, designed specifically for on-device and local inference, and it can be quickly loaded and run via Ollama on ordinary consumer hardware without sending data to the cloud.
50%UnverifiedSetting ort.wasm.wasmPaths to point to the regular WebAssembly build before loading any model allows 4-bit Gemma 3 270M (about 323 MB) to successfully load and run on Chrome's CPU.
50%UnverifiedCandidate small models include SmolLM2 (135M and 360M), Gemma 3 270M, LFM2.5-350M, Qwen2.5-0.5B, and Qwen3-0.6B, all of which have ONNX browser builds.
50%UnverifiedIn an evaluation of 30 answerable questions, off-the-shelf small models under 350MB achieved faithfulness (all assertions can be found in the passages) at most 3 times.
50%UnverifiedZero-shot Gemma 3 270M is nearly unusable on the grammar correction task, with an F0.5 of only 0.122, and 99.6% of correct sentences were altered.
50%