PulseAugur
中
实时 13:27:10

定制的四卡P100配置的Qwen3.8模型达到33.4 tps

一位用户分享了为运行大型语言模型而定制的服务器硬件的遥测数据。该配置配备了四块NVIDIA Tesla P100 GPU,总显存为64GB,其中58.7GB用于运行。通过Strata框架运行1200亿参数的Qwen3.8模型时,该配置实现了33.4 tokens/秒的输出生成速度和47 tokens/秒的提示预填充速度。系统运行效率高,温度保持在72°C,功耗仅为170W。 AI

影响 展示了在本地运行大型语言模型的硬件利用效率。

排序理由 用户生成的关于运行LLM的定制硬件配置的遥测数据。

在 Mastodon — fosstodon.org 阅读 →

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

定制的四卡P100配置的Qwen3.8模型达到33.4 tps

本文如何被排名

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
用户生成的关于运行LLM的定制硬件配置的遥测数据。
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
infra, model release
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]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    汪!这个搭载 Strata (120b QWEN3.8) 的四卡 P100 平台每秒处理 33.4 次。是的,它有效。速度很快。自定义四卡 NVIDIA Tesla P100 16GB 设置 (总共 64GB H 的遥测数据

    Dawg! 33.4 tps on this quad P100 rig running Strata (120b QWEN3.8). Yeah, it works. Fast. Telemetry for a custom quad NVIDIA Tesla P100 16GB setup (64GB total HBM2 VRAM) running alongside 128GB of system DDR3 memory. The system shows 58.7 GB of VRAM actively allocated across all …