Monday, November 16, 2026
  • About
  • Advertise
  • Privacy & Policy
  • Contact
Unlock Your Potential With AI | AI Mind Center
  • AI News & Trends

    Edge0-145B on a laptop? The 29GB claim, checked

    Gemini2.5 Pro (I/O edition) First Look: How to Get Access

    Gemini2.5 Pro (I/O edition) First Look: How to Get Access

    May the Fourth be with you: Launching AI MIND CENTER

    May the Fourth be with you: Launching AI MIND CENTER

  • AI Productivity Tools

    Seedream 5.5 blind test: FLUX 3 quality, 15x cheaper

    AI influencer character reference and cloned voice waveform on the left, three phone videos of the character on the right

    How to Create an AI Influencer: The Full Pipeline, the Failures, and What It Actually Costs

    The 17 AI Tools Actually Worth Using in 2026

    ⚡ Best AI Writing Tools 2025: Transform Your Content Creation Game

    ⚡ Best AI Writing Tools 2025: Transform Your Content Creation Game

    Top 15 AI Tools Every Developer Should Be Using in 2025

    Top 15 AI Tools Every Developer Should Be Using in 2025

  • AI for Developers
    Getting Started with OpenAI’s API: A Practical Guide for Developers (2026 Edition)

    Getting Started with OpenAI’s API: A Practical Guide for Developers (2026 Edition)

    How to Use GitHub Copilot: From Beginner to Advanced (Complete 2026 Guide)

    Streamlining Workflows with Semantic Kernel

    Streamlining Workflows with Semantic Kernel

    Step-by-Step: Setting Up Microsoft.Extensions.AI

    Step-by-Step: Setting Up Microsoft.Extensions.AI

    Running IA Locally with Ollama with .NET

    Running IA Locally with Ollama with .NET

  • AI in Game Development

    The Ultimate Guide to AI-Generated Assets in Unreal Engine 5.3

    7 AI Game Development Tools that Are Changing the Industry

    7 AI Game Development Tools that Are Changing the Industry

  • AI Agents & Automation
No Result
View All Result
  • AI News & Trends

    Edge0-145B on a laptop? The 29GB claim, checked

    Gemini2.5 Pro (I/O edition) First Look: How to Get Access

    Gemini2.5 Pro (I/O edition) First Look: How to Get Access

    May the Fourth be with you: Launching AI MIND CENTER

    May the Fourth be with you: Launching AI MIND CENTER

  • AI Productivity Tools

    Seedream 5.5 blind test: FLUX 3 quality, 15x cheaper

    AI influencer character reference and cloned voice waveform on the left, three phone videos of the character on the right

    How to Create an AI Influencer: The Full Pipeline, the Failures, and What It Actually Costs

    The 17 AI Tools Actually Worth Using in 2026

    ⚡ Best AI Writing Tools 2025: Transform Your Content Creation Game

    ⚡ Best AI Writing Tools 2025: Transform Your Content Creation Game

    Top 15 AI Tools Every Developer Should Be Using in 2025

    Top 15 AI Tools Every Developer Should Be Using in 2025

  • AI for Developers
    Getting Started with OpenAI’s API: A Practical Guide for Developers (2026 Edition)

    Getting Started with OpenAI’s API: A Practical Guide for Developers (2026 Edition)

    How to Use GitHub Copilot: From Beginner to Advanced (Complete 2026 Guide)

    Streamlining Workflows with Semantic Kernel

    Streamlining Workflows with Semantic Kernel

    Step-by-Step: Setting Up Microsoft.Extensions.AI

    Step-by-Step: Setting Up Microsoft.Extensions.AI

    Running IA Locally with Ollama with .NET

    Running IA Locally with Ollama with .NET

  • AI in Game Development

    The Ultimate Guide to AI-Generated Assets in Unreal Engine 5.3

    7 AI Game Development Tools that Are Changing the Industry

    7 AI Game Development Tools that Are Changing the Industry

  • AI Agents & Automation
No Result
View All Result
Unlock Your Potential With AI | AI Mind Center
No Result
View All Result
Home AI News & Trends

Edge0-145B on a laptop? The 29GB claim, checked

Felipe Machado by Felipe Machado
November 15, 2026
in AI News & Trends
9
0
16
SHARES
130
VIEWS
Share on FacebookShare on XShare on Linkedin

Edge0 says its 145B open-weights model “runs locally on a compatible laptop, with reported peak memory of 29GB”. The model card measures 23.25 GiB of VRAM plus 38.27 GiB of host RAM, on a desktop RTX 5090 D.

Table from the Edge0 announcement showing 29GB peak memory and: Runs on a compatible personal laptop, such as a MacBook Pro, without a server
Table from the Edge0 announcement showing 29GB peak memory and: Runs on a compatible personal laptop, such as a MacBook Pro, without a server

Both numbers can be true, but the sources never say exactly what the 29GB measures. The gap decides whether you can run it. This is our reading of the sources. We did not run the model ourselves.

Note from the Edge0-145B-NVFP4 model card: With residency enabled, 145B NVFP4 used 23.25 GiB VRAM + 38.27 GiB host RAM on RTX 5090 D 24 GB
Note from the Edge0-145B-NVFP4 model card: With residency enabled, 145B NVFP4 used 23.25 GiB VRAM + 38.27 GiB host RAM on RTX 5090 D 24 GB

The facts

  • The claim. 145B parameters, about 10B active per step, “29GB peak memory”, decoding above 80 tokens/s, per the Edge0 announcement (12 Nov). The same post says “28GB” further down, and “a 48GB laptop”.
  • Three tiers. “Hot experts” sit on the GPU, “an expert library of approximately 40GB sits in system memory”, and “approximately 48GB of vocabulary data resides on the SSD and is read on demand”, per the same post. So 29GB is a peak, not the size of the model.
  • The card. NVFP4 weights are 47.79 GiB. Q3_K weights are 40.81 GiB (23.14 GiB VRAM plus 31.28 GiB RAM). Per the model card.
  • Speed. The headline figures are measured on “RTX 5090 D 24 GB”, per the card. No machine in the speed table is labelled a laptop.
Speed table from the Edge0-145B model card with chat decode and agent decode in tokens per second for each machine and build
Speed table from the Edge0-145B model card with chat decode and agent decode in tokens per second for each machine and build

What it changes

Hardware, as listed on the model card (tok/s, chat decode / agent decode):

Machine Build Chat Agent
RTX 5090 D Q3_K 99.7 121.2
RTX 5090 D NVFP4 79.6 98.3
RTX 4090 Q3_K 69.9 91.7
RTX Spark N1X, 60 GiB Q3_K 37.7 36.7
RTX Spark N1X, 60 GiB NVFP4 40.1 46.0
Apple M2 Ultra (Metal) Q3_K 60.9 57.0
16 GiB VRAM + 20 GiB RAM Q3_K 36.8 44.9

The last row is the same RTX 5090 D, which Edge0 capped to 16 GiB of VRAM and 20 GiB of RAM for the test. It is the closest the card gets to a smaller machine, and it still ran Q3_K at 36.8 tok/s chat decode. Now add up the card’s own numbers: 23.25 + 38.27 is about 61.5 GiB of fast memory for NVFP4, before the SSD part. That is why “laptop” needs the word “compatible”, and why we would not buy hardware on the 29GB figure.

Which build. Q3_K is smaller (40.81 vs 47.79 GiB) and faster on the 5090 D (99.7 vs 79.6 chat). It is also the build with Metal instructions for Apple Silicon, according to the card. NVFP4 is CUDA only. The card gives size and speed, so that is all we compare.

Start the server. You build edge0-infer from the repo first (the card links the build steps). Then the card gives one command:

edge0-infer serve --model /path/to/Edge0-145B-NVFP4

It prints “Listening: http://127.0.0.1:8000” and exposes OpenAI-compatible and Anthropic-compatible endpoints. Build steps are in the repo (Apache-2.0 for the framework code).

What the licence forbids. The model uses the Edge0 Community Model License 1.0 plus the Qwen Community License 1.0. Personal use, research, modification, non-commercial sharing, internal use and commercial use of the outputs are allowed. “Selling or commercially bundling the model, operating a commercial model service, or offering an independent commercial coding or office assistant using it requires a separate written Edge0 license.”

License paragraph from the Edge0-145B model card about selling, bundling or operating a commercial service with the model requiring a separate written Edge0 license
License paragraph from the Edge0-145B model card about selling, bundling or operating a commercial service with the model requiring a separate written Edge0 license

App developers: if you already point a client at an OpenAI-style URL, the card says this server speaks that protocol. We did not test your client.

Creators and solo founders: use it for your own work and sell what it produces, subject to the upstream Qwen terms. Do not build a paid assistant on top of it without Edge0’s written licence. On a 5090 D the card reports 98.3 tok/s agent decode (NVFP4).

Game devs: the Edge0 blog shows its own demos of playable games and a medieval city built in Blender. We did not verify or reproduce them. Treat them as marketing until someone else does, and only consider it if you already own a 24 GB card and the RAM listed above.

Caveats

  • Benchmarks are Edge0’s own. “Edge0, Qwen, DeepSeek, and Claude results come from Edge0’s internal evaluations”, and the technical report is “being released”.
  • On Terminal-Bench 2.1 Edge0 scores 86.52 against 83.3 for Qwen3.8-Flash-Next. On HLE it scores 35.4 against 35.9, and Claude-Opus-4.6 Max scores 40.0.
Benchmark table from the Edge0 announcement comparing Edge0-145B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash-0731 and Claude-Opus-4.6 Max
Benchmark table from the Edge0 announcement comparing Edge0-145B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash-0731 and Claude-Opus-4.6 Max
  • The rival memory figures (Qwen about 70GB, DeepSeek about 87GB) are estimates that “remain to be measured”.
  • The card says Edge0 is “not a relabelled Qwen3.8-Flash-Next, and not a re-quantization of it”.

Our take

Interesting weights, honest speed table, loose headline. If you have a 24 GB GPU and plenty of RAM, it is worth a look. If you have a regular laptop, wait for independent tests.

Sources

  • Introducing Edge0-145B, Edge0 blog, 12 Nov
  • Edge0-145B-NVFP4 model card, Hugging Face
  • Edge0-AI/Edge0, GitHub
Felipe Machado

Felipe Machado

I'm truly excited about what AI has to offer—especially in how it can unlock our potential across every area of life. I dive deep into a variety of AI-related topics and share the most valuable insights and tools I've discovered that are helping me every day. That way, you don’t have to spend hours researching—I’ve done the hard work for you, so you can save time and focus on what matters most.

Related Posts

Gemini2.5 Pro (I/O edition) First Look: How to Get Access
AI News & Trends

Gemini2.5 Pro (I/O edition) First Look: How to Get Access

May 8, 2025
May the Fourth be with you: Launching AI MIND CENTER
AI News & Trends

May the Fourth be with you: Launching AI MIND CENTER

May 4, 2025

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

I agree to the Terms & Conditions and Privacy Policy.

Unlock Your Potential With AI | AI Mind Center

Unlock your potential with AI Mind Center! Explore AI tools, tutorials, and inspiration to grow, create, and geek out.

Follow Us

Subscribe to our newsletter!

Browse by Category

  • AI Agents & Automation
  • AI for Developers
  • AI in Game Development
  • AI News & Trends
  • AI Productivity Tools

Recent News

Edge0-145B on a laptop? The 29GB claim, checked

November 15, 2026

AWS Emulator: Free, Local, and Written by Agents

November 15, 2026

Gemini Orchestrator: Plan Expensive, Build Cheap

November 13, 2026
  • About
  • Advertise
  • Privacy & Policy
  • Contact

© 2026 | Website Made By aimindcenter.com.

Welcome Back!

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • AI News & Trends
  • AI Productivity Tools
  • AI in Game Development
  • AI for Developers
  • AI Agents & Automation

© 2026 | Website Made By aimindcenter.com.

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy and Cookie Policy.