Spark cluster with Qwen3.5

Alex Ziskind · 64.8K views · 1.6K likes Short

Analysis Summary

30% Minimal Influence

mildmoderatesevere

“Be aware that the 'throttling' headlines mentioned in the description are used as a hook to frame the hardware in a heroic light, potentially encouraging a preference for high-end enterprise gear over consumer alternatives.”

Ask yourself: “Did I notice what this video wanted from me, and did I decide freely to say yes?”

Transparency Transparent

Human Detected

95%

Signals

The transcript exhibits clear markers of natural human speech, including spontaneous corrections, informal vocabulary, and non-formulaic pacing. The content is highly specific to hands-on hardware testing, which aligns with the creator's established persona and expertise.

Speech Patterns Use of filler words ('uh', 'well'), colloquialisms ('chunky model'), and natural self-correction ('Well, you know, unified memory on Sparks, that's what it's called').

Narrative Style Personalized testing approach ('Let's do a Llama Beni test, shall we?') and subjective evaluation ('It's not bad').

Channel History Established niche creator (Alex Ziskind) with a consistent history of hands-on hardware testing and developer-focused content.

Worth Noting

Positive elements

Provides real-world performance benchmarks (tokens per second) for the Qwen 3.5 model on specialized NVIDIA hardware clusters.

Be Aware

Cautionary elements

The framing of 'debunking' throttling headlines may lead viewers to overlook the diminishing returns of enterprise hardware for standard developer workflows.

Influence Dimensions

How are these scored?

About this analysis

Knowing about these techniques makes them visible, not powerless. The ones that work best on you are the ones that match beliefs you already hold.

This analysis is a tool for your own thinking — what you do with it is up to you.

Analyzed March 13, 2026 at 16:07 UTC Model google/gemini-3-flash-preview-20251217 Prompt Pack bouncer_influence_analyzer 2026-03-08a App Version 0.1.0

More on This Topic

Related content covering similar topics.

Why Infrastructure Decisions Will Define AI Experiences in 2026 | Danielle Cook, Akamai

TFiR

Low Mostly Transparent

edge computing ai infrastructure

Transcript

Quen 3.5 pretty big big chunky model 397 billion parameters and about 807 gigabytes on disk. That's a lot. It can fit on this though because this is about a terabyte of VRAM. Well, you know, unified memory on Sparks, that's what it's called. But, uh, yeah, you need a lot of RAM to be able to run. One Mac Studio won't be able to run that. You should be able to run it on two Mac Studios clustered together. Let's do a Llama Beni test, shall we? Llama Beni go. And there's NVtop. You can see it working on all the machines. 112 gigs of RAM being used per node. That's a lot. And we're done. We're getting 23.5 tokens per second generation and prompt processing 1,400 tokens per second. It's not bad. It's not bad considering it's a state-of-the-art model, does really well on tests, and it can run in your home.

Video description

Stress-testing the NVIDIA DGX Spark, Dell Pro Max GB10, ASUS Ascent GX10, and MSI Edge Expert revealed the real limiter behind the “throttling” headlines. My USB-C portable hub: https://amzn.to/4kw0hrf 👀 My favorite external drive (dependable): https://amzn.to/3Os9Wi3 👀 Thunderbolt 4 dock: https://amzn.to/3yVRicC 👀 Thor on NVIDIA Marketplace: https://bit.ly/44j0acY 👀 Spark and Thor on Amazon: https://bit.ly/4pCjBpJ 👀 M4 Pro Mac Mini deal: https://amzn.to/3Mw8dNx ⚡ *Other gear I use:* https://www.amazon.com/shop/alexziskind 🎥 Related Videos 🎥 🧬🐍 Mac Studio CLUSTER vs M3 Ultra 🤯 - https://youtu.be/d8yS-2OyJhw 🧳🧰 Mini PC portable setup - https://youtu.be/4RYmsrarOSw 🍎💻 Dev setup on Mac - https://youtu.be/KiKUN4i1SeU 💸🧠 Cheap mini runs a 70B LLM 🤯 - https://youtu.be/xyKEQjUzfAk 🧪🔥 RAM torture test on Mac - https://youtu.be/l3zIwPgan7M 🍏⚡ FREE Local LLMs on Apple Silicon | FAST! - https://youtu.be/bp2eev21Qfo 🧠📉 REALITY vs Apple’s Memory Claims | vs RTX4090m - https://youtu.be/fdvzQAWXU7A ⚡💥 Thunderbolt 5 BREAKS Apple’s Upcharge - https://youtu.be/nHqrvxcRc7o 🧠🚀 INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k 🧱🖥️ Mac Mini Cluster - https://youtu.be/GBR6pHZ68Ho * 🛠️ Developer productivity Playlist - https://www.youtube.com/playlist?list=PLPwbI_iIX3aQCRdFGM7j4TY_7STfv2aXX — — — — — — — — — ❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺 Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1 Join this channel to get access to perks: https://www.youtube.com/channel/UCajiMK_CY9icRhLepS8_3ug/join — — — — — — — — — 📱LET'S CONNECT ON SOCIAL MEDIA ALEX ON TWITTER: https://twitter.com/digitalix — — — — — — — — — #dgxspark #nvidia #llm