# Qwen3 0.6B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/qwen3-0-6b/

Provider: Alibaba. Nominal parameters: 0.6B. [Upstream model card](https://huggingface.co/Qwen/Qwen3-0.6B).

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

- Qwen3-0.6B-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 8c14ce481d4c692769976ad52afea453a102df19. [Pinned model files](https://huggingface.co/mlc-ai/Qwen3-0.6B-q4f16_1-MLC/resolve/8c14ce481d4c692769976ad52afea453a102df19/).
- Qwen3-0.6B-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision 9b4f0b05b08c692ea86fe151ea878406ad22f428. [Pinned model files](https://huggingface.co/mlc-ai/Qwen3-0.6B-q4f32_1-MLC/resolve/9b4f0b05b08c692ea86fe151ea878406ad22f428/).
- Qwen3-0.6B-q0f16-MLC: q0f16; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 2d6c15b9dd8b99e021d978ada68faebbcfc12bb9. [Pinned model files](https://huggingface.co/mlc-ai/Qwen3-0.6B-q0f16-MLC/resolve/2d6c15b9dd8b99e021d978ada68faebbcfc12bb9/).

## Published evidence

### q4f16_1 — 8f7ee1ba-397b-4e19-9cef-c160f11bb72e

Captured: 2026-10-18T06:19:12.176Z. 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: 50.

- Median runtime-reported decode speed: 38.70 tok/s.
- Median first-output latency: 52.85 ms.
- Median actual response time: 1.35 s.
- Sampled peak Chrome footprint: 3.73 GB.
- [Raw published JSON report](https://browserllm.dev/reports/8f7ee1ba-397b-4e19-9cef-c160f11bb72e.json).