PulseAugur
EN
LIVE 14:00:26

Llama 3 runs at 6 tokens/sec on laptop CPU, revealing performance insights

By PulseAugur Editorial · [1 sources] ·

A user successfully ran an 8-billion-parameter Llama 3 model on a standard HP laptop with an i7-1165G7 CPU and 12GB of RAM, achieving a speed of 6 tokens per second. The experiment revealed that the integrated Iris Xe GPU was faster for prompt reading but slower for answer generation compared to the CPU, likely due to shared memory bandwidth. Additionally, using an 8-bit KV cache proved less efficient than a 16-bit cache for longer tasks, and capping the CPU's power consumption did not impact writing speed while preventing overheating. AI

IMPACT Demonstrates feasibility of running moderately sized LLMs on standard laptops, potentially lowering barriers to local AI experimentation.

RANK_REASON User-level experimentation with running an existing LLM on consumer hardware.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Llama 3 runs at 6 tokens/sec on laptop CPU, revealing performance insights

How we ranked this

Signal score
20 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
User-level experimentation with running an existing LLM on consumer hardware.
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
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.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Tekk_73 ·

    An 8B SLM on a 4-core laptop CPU, no GPU: 6 tokens/sec

    <p>I ran an 8-billion-parameter Llama-3 model (Q4_K_M) on an HP laptop with an i7-1165G7, 12 GB of RAM and no discrete GPU.</p> <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Measurement</th> <th>Result</th> </tr> </thead> <tbody> <tr> <td>Writing speed (fresh chat…

RELATED ENTITIES

RELATED TOPICS