# Llama 3.2 1B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/llama-3-2-1b/

Provider: Meta. Nominal parameters: 1B. [Upstream model card](https://huggingface.co/meta-llama/Llama-3.2-1B-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

- Llama-3.2-1B-Instruct-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 2a37b0a5ecb622d51ddc2fac74de0b95872affd7. [Pinned model files](https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q4f16_1-MLC/resolve/2a37b0a5ecb622d51ddc2fac74de0b95872affd7/).
- Llama-3.2-1B-Instruct-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision a949835e0f9a65335bd834db02a44cf8fae34020. [Pinned model files](https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q4f32_1-MLC/resolve/a949835e0f9a65335bd834db02a44cf8fae34020/).
- Llama-3.2-1B-Instruct-q0f16-MLC: q0f16; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 2c52165f529227534c21d83f140293d86f4eaaa3. [Pinned model files](https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q0f16-MLC/resolve/2c52165f529227534c21d83f140293d86f4eaaa3/).

## Published evidence

### q4f16_1 — f9fe3b3d-8ca7-4e62-9f4a-14027da28cef

Captured: 2026-10-18T07:29:46.286Z. WebLLM 0.2.82; Chrome 155.0.0.0; M5 Pro · 48 GB · dedicated Chrome. Protocol: 60 requests · 3 × 20 · 90 s idle. Completed measured requests: 1. Output tokens per request: 63.

- Median runtime-reported decode speed: 163.55 tok/s.
- Median first-output latency: 26.25 ms.
- Median actual response time: 0.42 s.
- Sampled peak Chrome footprint: 3.82 GB.
- [Raw published JSON report](https://browserllm.dev/reports/f9fe3b3d-8ca7-4e62-9f4a-14027da28cef.json).