# OpenRouter finds no accuracy gap between fp8, fp4 and fp16 for Qwen3.8 27B

> Original title: LLM Quantization: What fp8 and fp4 Do to Quality and Price

- Source: OpenRouter Blog
- Published: 2026-11-11T00:00:00.000Z
- Bad Influence: https://badinfluence.news/items/lg7mcv98679tar2blb9ip5q73
- Original: https://openrouter.ai/blog/insights/llm-quantization/

## Summary

OpenRouter tested six endpoints serving Qwen3.8 27B on October 20, 2026, and found no accuracy difference between fp16, fp8 and fp4, with all scoring 98.3% to 99.2% on 240 tasks. Lower precision was usually cheaper, with 4-bit cheaper than 8-bit for 26 of 33 models, though 8-bit was more expensive than 16-bit for 7 of 24 models served at both. One fp4 endpoint scored lowest on 40 multiplication tasks, a gap OpenRouter said was too small to rule out chance.