Sparsh Kandpal

An AI Engineer navigating through the landscapes of entrepreneurship and innovation

[Sparsh Kandpal @SparshKandpal2]

Built for the Hermes Agent Business Hackathon , Recoup helps recover the $355B owed to 36M US small businesses using an AI agent that chases, negotiates, and collects via Stripe.@NousResearch @nvidia @stripe @NVIDIAAI @NVIDIARTXSpark

[Ahmad @TheAhmadOsman]

Local AI hardware = capacity × bandwidth × software stack

- Capacity tells you what fits
- Bandwidth tells you how hard the box can breathe
- The software stack tells you how much of the spec sheet you can actually cash out.

Hardware by Memory Bandwidth
- Mac Studio M3 Ultra: up to 512GB @ 819 GB/s
- RTX PRO 6000 Blackwell: 96GB @ 1792 GB/s
- RTX 5090: 32GB @ 1792 GB/s
- RTX 4090: 24GB @ 1008 GB/s
- RX 7900 XTX: 24GB @ 960 GB/s
- Radeon PRO W7900: 48GB @ 864 GB/s
- AMD Radeon AI PRO R9700: 32GB @ 640 GB/s
- Intel Arc Pro B65: 32GB @ ~608 GB/s
- Tenstorrent Wormhole n300: 24GB @ 576 GB/s
- Tenstorrent Blackhole p150: 32GB @ 512 GB/s + 800G
- MacBook Pro M5 Max: 460-614 GB/s
- MacBook Pro M5 Pro: 307 GB/s
- DGX Spark: 128GB @ 273 GB/s (coherent + CUDA)
- Mac mini M4 Pro: 273 GB/s
- Ryzen AI Max / Strix Halo: ~256 GB/s (~96GB usable GPU)
- MacBook Air M5: 153 GB/s
- Snapdragon X2 Elite: 152-228 GB/s
- Intel Lunar Lake: 136 GB/s
- Snapdragon X Elite: 135 GB/s
- Mac mini M4: 120 GB/s
- Arc Pro B60: 24GB @ ~456 GB/s

Verdict

- GPUs are still the bandwidth kings

- Apple wins: stupid amounts of memory, don’t want to shard across GPUs
- Apple loses: when raw tokens/sec & concurrency matter more

- DGX Spark: coherent memory + NVIDIA stack

- Strix Halo / Ryzen AI Max: first real x86 unified-memory contender

- Tenstorrent: fully OSS stack, excited to see this mature

Fitting ≠ serving

Even if it fits, you still pay for
- bandwidth during decode
- KV cache growth
- dequantization
- batching + concurrency
- scheduler quality
- framework overhead

The only mental model that matters:

1. What must fit?
2. What bandwidth tier do I need?
3. What software stack can actually deliver it?

In short:
- NVIDIA → fastest raw speed
- Apple Studio M3 Ultra → biggest one-box memory
- Strix Halo → first real x86 unified
- DGX Spark → coherent NVIDIA dev appliance
- AMD / Intel Arc → rising alternatives
- Tenstorrent → fully opensource stack

Do ask: “which bottleneck am I buying?”

Not: “which hardware is best?”

[Spandan Mukherjee @spandan_twts]

EP219: 12 Open-source LLMs via @dailydotdev https://t.co/TPWIARqruo

[NVIDIA AI @NVIDIAAI]

Love seeing photos like this.

Let's see some more setups.

Curious what everyone's running these days. What models are you using and what are you building?

[Andrej Karpathy @karpathy]

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.

I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

[NVIDIA AI @NVIDIAAI]

OpenShell v0.0.55

🧩 Google Vertex AI inference provider
🔒 Profile-backed policy visibility
🐳 Better Podman detection in the gateway
🖥️ Restored GPU procfs baseline behavior
🔧 CI and docs fixes

Run agents against Vertex AI, with improved policy visibility and more reliable Podman and GPU sandbox behavior.

https://t.co/TRlhGwfF8D

[ClaudeDevs @ClaudeDevs]

Opus 4.8 is live in Claude Code today.

A few things worth knowing: 🧵

[Sparsh Kandpal @SparshKandpal2]

@spandan_twts Hell Nahhh!!!

[Sparsh Kandpal @SparshKandpal2]

@GoibiboSupport @goibibo
URGENT: Confirmed hotel booking denied at check-in.
Hotel says booking not received and it's a case of overbooking also claiming it's a glitch ,Stranded at the night and forced to book another hotel .
Need immediate help.
Booking ID: GH26113262471876