# Gemma 2 2B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/gemma-2-2b/

Provider: Google. Nominal parameters: 2B. [Upstream model card](https://huggingface.co/google/gemma-2-2b-it).

Measurements describe an exact model artifact, quantization, runtime, browser, device, workload and cache state. Performance medians exclude warmup. Tokenizers and actual output lengths differ across models. These tests do not measure intelligence or task quality; no overall model score is assigned. Missing telemetry is unavailable, never zero. CPU is dedicated Chrome process-tree capacity; Chrome GPU time is experimental driver-accounted time including rendering, not GPU utilization. Power is whole-host subsystem power, not model-only power. Browser memory is summed process footprint, not deduplicated RAM.

## Pinned runnable artifacts

- gemma-2-2b-it-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision de9cc76f0d4b3a49a0f718df424944054bf1eec1. [Pinned model files](https://huggingface.co/mlc-ai/gemma-2-2b-it-q4f16_1-MLC/resolve/de9cc76f0d4b3a49a0f718df424944054bf1eec1/).
- gemma-2-2b-it-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision 5389274865dee69fc1c0f44af37990d933fb4c47. [Pinned model files](https://huggingface.co/mlc-ai/gemma-2-2b-it-q4f32_1-MLC/resolve/5389274865dee69fc1c0f44af37990d933fb4c47/).

## Published evidence

No measured report is published for this model yet. Available artifacts do not establish performance or device compatibility.