English(EN) Qwen3.5 122B A10B (Non-reasoning) hits 147.6 tokens/sec and 16.1 intelligence points per dollar — independently measured, not vendor claims. How does that compa

Qwen3.5 122B A10B 模型展现出强劲的性能和效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 11:01

Qwen3.5 122B A10B 模型，特别是其非推理能力，已达到每秒 147.6 个 token 的性能基准。此外，它还展示了每美元 16.1 个智能点的效率。这些指标均经过独立验证，区别于供应商提供的声明。 AI

影响独立验证的性能指标提供了对模型能力和效率更清晰的理解。

排序理由该条目报告了 AI 模型的独立测量基准测试结果。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

Qwen3.5 122B

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目报告了 AI 模型的独立测量基准测试结果。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech · 2026-09-10 11:01

Qwen3.5 122B A10B（非推理）独立测量达到每秒147.6个token和每美元16.1个智能点——独立测量，非厂商宣称。与此相比如何？

Qwen3.5 122B A10B (Non-reasoning) hits 147.6 tokens/sec and 16.1 intelligence points per dollar — independently measured, not vendor claims. How does that compare? https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI

链接 olud.ai/leaderboard.html

本文如何被排名

报道来源 [1]

Qwen3.5 122B A10B（非推理）独立测量达到每秒147.6个token和每美元16.1个智能点——独立测量，非厂商宣称。与此相比如何？

相关实体

相关话题