# Qwen2.5 0.5B browser LLM configuration and benchmarks

Canonical page: https://browserllm.dev/models/qwen2-5-0-5b/

Provider: Alibaba. Nominal parameters: 0.5B. [Upstream model card](https://huggingface.co/Qwen/Qwen2.5-0.5B-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

- Qwen2.5-0.5B-Instruct-q4f16_1-MLC: q4f16_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 32ff081fe7e4dfe4ffb167b94c66fdf11e02b8ad. [Pinned model files](https://huggingface.co/mlc-ai/Qwen2.5-0.5B-Instruct-q4f16_1-MLC/resolve/32ff081fe7e4dfe4ffb167b94c66fdf11e02b8ad/).
- Qwen2.5-0.5B-Instruct-q4f32_1-MLC: q4f32_1; WebLLM 0.2.82; context limit 4096 tokens; required shader features none beyond WebGPU; revision 8e6ec5f417c7d0e1414703ef619b8a24686e3ab0. [Pinned model files](https://huggingface.co/mlc-ai/Qwen2.5-0.5B-Instruct-q4f32_1-MLC/resolve/8e6ec5f417c7d0e1414703ef619b8a24686e3ab0/).
- Qwen2.5-0.5B-Instruct-q0f16-MLC: q0f16; WebLLM 0.2.82; context limit 4096 tokens; required shader features shader-f16; revision 50d03840389a3a828c40c9b2573acf82bf1bb2de. [Pinned model files](https://huggingface.co/mlc-ai/Qwen2.5-0.5B-Instruct-q0f16-MLC/resolve/50d03840389a3a828c40c9b2573acf82bf1bb2de/).

## Published evidence

### q4f16_1 — cb3ad0f9-ce2b-4bc9-a9e2-8c56411d449b

Captured: 2026-10-18T06:57:28.253Z. 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: 113.83 tok/s.
- Median first-output latency: 40.15 ms.
- Median actual response time: 0.60 s.
- Sampled peak Chrome footprint: 2.70 GB.
- [Raw published JSON report](https://browserllm.dev/reports/cb3ad0f9-ce2b-4bc9-a9e2-8c56411d449b.json).