PulseAugur
EN
LIVE 22:19:03

Surface Laptop Ultra excels at short coding tasks with Qwen3 coder 30B via Ollama

By PulseAugur Editorial · [1 sources] ·

A Surface Laptop Ultra equipped with an Nvidia RTX Spark N1X GPU achieved impressive speeds of 90.9 tokens per second when running the Qwen3 coder 30B model locally using Ollama for short coding tasks. This performance is notably faster than a Lenovo Yoga 9n on the same hardware for similar tasks. However, when processing a very long prompt of over 100,000 tokens, the Surface Laptop Ultra's performance significantly degraded to 19.7 tokens per second, while the Lenovo setup with a more optimized vLLM configuration maintained a much higher speed of 44.3 tokens per second. AI

IMPACT Demonstrates practical performance differences for local LLM deployment on consumer hardware, highlighting trade-offs between ease of use and long-context efficiency.

RANK_REASON The article details the performance of a specific hardware and software setup for running a local LLM, focusing on practical usage rather than a novel release or research breakthrough.

Read on dev.to — LLM tag →

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

Surface Laptop Ultra excels at short coding tasks with Qwen3 coder 30B via Ollama

How we ranked this

Signal score
22 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The article details the performance of a specific hardware and software setup for running a local LLM, focusing on practical usage rather than a novel release or research breakthrough.
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
product, 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) · Steef-Jan Wiggers ·

    Qwen3-Coder 30B on a Surface Laptop Ultra: run it on RTX Spark with Ollama

    <p>My Surface Laptop Ultra decodes short code replies from qwen3-coder:30b at <strong>90.9 tokens a second</strong>, twice the 44.7 that <a href="https://techcommunity.microsoft.com/blog/AppsonAzureBlog/qwen3-8-27b-on-a-lenovo-laptop-run-it-on-rtx-spark-watch-it-in-azure-monitor/…

RELATED ENTITIES

RELATED TOPICS