# Qwen3 4B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/qwen3-4b/

Provider: Alibaba. Nominal parameters: 4B. [Upstream model card](https://huggingface.co/Qwen/Qwen3-4B).

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

- Qwen3-4B-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision a5c9fab855e3ccbdfed2e7e69683d75f30332161. [Pinned model files](https://huggingface.co/mlc-ai/Qwen3-4B-q4f16_1-MLC/resolve/a5c9fab855e3ccbdfed2e7e69683d75f30332161/).
- Qwen3-4B-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision b7e4eb1ba80728187fb5df44055cc1a7c32310e0. [Pinned model files](https://huggingface.co/mlc-ai/Qwen3-4B-q4f32_1-MLC/resolve/b7e4eb1ba80728187fb5df44055cc1a7c32310e0/).

## Published evidence

### q4f16_1 — 15427e99-ceb7-4261-b22a-22dfde0d52ad

Captured: 2026-10-18T06:27:03.831Z. 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: 59.

- Median runtime-reported decode speed: 29.63 tok/s.
- Median first-output latency: 102.55 ms.
- Median actual response time: 2.10 s.
- Sampled peak Chrome footprint: 6.63 GB.
- [Raw published JSON report](https://browserllm.dev/reports/15427e99-ceb7-4261-b22a-22dfde0d52ad.json).