# SmolLM2 1.7B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/smollm2-1-7b/

Provider: Hugging Face. Nominal parameters: 1.7B. [Upstream model card](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct).

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

- SmolLM2-1.7B-Instruct-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 84f57f8580a9d8d623266b600ad4273bb9fd84c1. [Pinned model files](https://huggingface.co/mlc-ai/SmolLM2-1.7B-Instruct-q4f16_1-MLC/resolve/84f57f8580a9d8d623266b600ad4273bb9fd84c1/).
- SmolLM2-1.7B-Instruct-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision 0b81fd80381d396f37216e4c74e958024c589e24. [Pinned model files](https://huggingface.co/mlc-ai/SmolLM2-1.7B-Instruct-q4f32_1-MLC/resolve/0b81fd80381d396f37216e4c74e958024c589e24/).

## Published evidence

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