雷峰網模型更新

一臺手掌大小、300克的AI主機,為什麼能跑122B模型?

2026年5月25日 10:41

重點摘要

聯想推出僅300克、手掌大小的AI主機P7,能在30W功耗下提供190TOPS算力,並於本地運行122B參數模型。此設備專為Agent時代設計,可7×24小時低功耗、靜音運作,並採用存算一體架

站內 AI 整理稿

### 手掌大小、300克的AI主機,為何能跑122B模型?重點整理與趨勢解析

近期,一款名為聯想AI主機P7的設備引起科技圈高度關注。它僅有手掌大小、重量約300克,卻能在本地運行高達122B參數的大語言模型,顛許了許多人對「大模型需要巨無霸工作站」的既有印象。這款主機的出現,不僅代表端側AI硬體邁入新階段,更揭示出Agent(自主代理)時代對於運算設備的全新需求:長期在線、低功耗、安靜且具備持續推理能力。

從規格來看,P7擁有190TOPS的異構AI算力,其中160TOPS來自後摩智能的存算一體晶片M50,整機功耗控制在30W以內,噪音低於35分貝,甚至可透過充電寶供電。這樣的設定,讓它有別於傳統AI PC或高階工作站,成為一種介於兩者之間的新型終端——Agent Computer。重點在於,它並非單純升級既有PC架構,而是從硬體到軟體都圍繞「長期執行Agent任務」重新設計,例如支援一機雙模,能在本地運行天禧Claw智能體,也能透過API接入外部模型。

背景脈絡方面,過去一年端側AI硬體的發展邏輯正在轉變。先有Mac mini因本地部署Agent而意外熱銷,後有英偉達DGX Spark以強大效能吸引開發者。然而,Mac mini難以支撐更大模型,DGX Spark則因價格與功耗難以大眾化。這凸顯出市場真正的缺口:一種能7×24小時穩定運行、功耗極低、體積小巧,卻又具備本地大模型推理能力的新設備。P7正是在此背景下誕生,它嘗試在效能與便攜之間找到平衡點,也驗證了存算一體架構在端側推理的可行性。

可能影響層面,這款設備的問世將對AI晶片與硬體市場產生深刻影響。傳統GPU路線在訓練階段稱霸,但在推理場景中,能效比與持續運作能力逐漸成為關鍵。存算一體技術透過減少數據搬運,大幅提升能效,使低功耗設備也能承擔千億參數模型推理。這可能促使更多廠商投入類似架構研發,甚至改變晶片競爭的規則——從追求峰值算力,轉向關注實際推理效率與長期穩定性。此外,P7的出現也讓Agent有機會從開發者實驗室走進消費級與行業應用,例如家用機器人、智能語音終端、邊緣網關等場景。

讀者可關注的後續發展,首先是聯想與後摩智能的深度合作是否會催生更多同類型產品,例如更小尺寸或更高階的AI主機。其次,存算一體技術的商業化進程值得留意,後摩智能已推出M50並建立完整產品矩陣,下一代晶片目標是進一步提升能效比,這可能影響未來端側AI裝置的效能天花板。最後,隨著Agent生態成熟,市場上將出現更多「Agent Computer」型態的設備,消費者可以期待更普及、更平價的本地AI終端,真正讓大模型成為日常生產力工具。整體而言,P7不僅是單一產品,更是AI硬體範式轉移的信號燈。

Related

相關文章

MarkTechPost AI模型更新

Liquid AI Introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: Dense Bi-Encoder and Late-Interaction Models for Fast Multilingual Search Across 11 Languages

This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M. Both hold 350M parameters. Both are the first bidirectional members of the LFM family. They build on LFM2.5-350M-Base, released in March. The pair targets fast multilingual and cross-lingual search across 11 languages. Their footprint is small enough to run almost anywhere. Both are available now on Hugging Face under the LFM Open License v1.0. LFM2.5 Retrievers The two models share one backbone but represent text differently. LFM2.5-Embedding-350M is a dense bi-encoder. It turns each document into a single vector. Pick it when you want the fastest search and the smallest, cheapest index. LFM2.5-ColBERT-350M is a late-interaction model. It converts each token into a vector rather

12 分鐘前
MarkTechPost AI模型更新

Perplexity Launches Brain, a Self-Improving Memory System That Builds a Context Graph of an Agent’s Work and Learns Overnight

Most AI memory remembers the user. It stores your preferences, your tastes, and your role. Perplexity is taking a different path. Today, Perplexity launched Brain, a self-improving memory system for its agent product, Computer. Brain does not focus on remembering you. It remembers what the agent did. That reframes what memory in AI is for. What is Perplexity‘s Brain Brain is a self-improving memory system. It builds a context graph of the work Computer performs. At set intervals, such as overnight, Brain reviews that graph. It then teaches itself how to do the work better. The idea is straightforward. The more work you do, the more efficient Brain makes your Computer. Brain is rolling out today to Perplexity Max and Enterprise Max subscribers in Research Preview. Two Axes of AI Memory Perp

14 小時前

智譜新高,MiniMax承壓,“大模型雙雄”命運殊途

這篇消息聚焦「智譜新高,MiniMax承壓,“大模型雙雄”命運殊途」。原始導語提到:大模型在被市場重新定價 從 AI 情報角度來看,這類內容值得關注其背後的技術進展、產品落地、產業競爭與後續市場影響。

16 小時前