Expired50% confidenceBenchmarkExact time

When the MTP draft depth is raised from the default 4 to 6 or 8, Qwen3.8-27B's output speed drops to 53.9 and 52.4 tokens/second respectively, below the default 55.1 tokens/second.

1

Sources

50%

Confidence

Short-term (~14 days)

Relevance

10/12/2026

First Seen

This claim has expired. It is kept for the record and no longer describes the current state.

Valid until: 10/26/2026(expired)

Sources

Qwen3.8 vs Ornith 1.5: Local Inference Speed and Code Review Benchmark on Mac

Related Entities

Qwen3.8-27Bmodel MTPconcept

Related Claims

UnverifiedQwen3.8-27B's output speed is 55.1 tokens/second, and Ornith 1.5's is 90.4 tokens/second.77% similar UnverifiedA speed of 4–5 tokens/second is too slow for practical use on an 8GB GPU; a 16GB GPU can improve this to 12–14 tokens/second, entering a practically usable range.70% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/1007480

API

curl https://kongchang.com/api/v1/knowledge/claims/1007480

MCP

get_claim(id=1007480)