ML

[ML @themachinescrew]

@ns123abc Moron take

[ML @themachinescrew]

@souchan_guitar Paul Gilbert the GOAT

[ML @themachinescrew]

@mil000 Really? I dont think so.

[ML @themachinescrew]

@washghost1 Piece of crap. Just replaced my “commercial” speed queen dryer with a Samsung & matching washer.

[Ahmad @TheAhmadOsman]

People ask why I keep insisting on GPUs
and not Mac Studios/Mac minis
for parallel & Agentic Workflows (multi-agents)

This is why:
- Llama 3.1 70B BF16 (~140GB w/o Context)
- on 8x RTX 3090s
- Synthetic data generation with
- 50+ concurrent requests
- Batch inference
- Sustained throughput

Not only that:
> ~2k context per request (prompt)
> ~1.8k tokens in output
> 2 mins 29 secs for 50 responses

This is GPU territory.
You can’t do this on a Mac.
Not yet at least.

[David Hendrickson @TeksEdge]

🔥 RTX 5090 + Gemma 4 31B: Real user testing right now

💳️ 32GB GDDR7 gives excellent headroom for higher quants on this dense 31B model.

🧪 Typical performance (llama.cpp + early user reports):

QuantApprox. VRAM (weights + overhead)Expected TPS (generation)
⚡ Q4_K_M ~18–21GB 55–75+ t/s
📈 Q5_K_XL ~22–25GB 45–65 t/s
🐢 Q6_K / Q8 ~26–32+GB 35–55 t/s

Users are actively testing 🐌 Unsloth UD-Q5_K_XL on RTX 5090 and tuning with TurboQuant / KV cache compression for better speed.

Great quality + performance balance for local Gemma 4 31B inference 👌

Who else is running it? 👀

[Ali Romman @aliromman_]

The DGX Spark is a ripoff.

$4,699 for 128GB of unified memory and 273 GB/s of bandwidth.

The Mac Studio M4 Max with 128GB of unified memory costs $3,699.

Same memory. $1,000 less. And it gets better.

The Mac Studio has double the bandwidth of the DGX Spark. For generating tokens, that means roughly twice as fast.

The Mac Studio is a full computer with or without AI. The DGX Spark is a $4,699 Linux box that does one thing.

NVIDIA announced this at $3,000. Shipped it at $4,000. Raised it to $4,700.

You're paying a $1,000 NVIDIA tax for half the bandwidth and fewer capabilities.

The only argument for DGX Spark is CUDA. If your entire workflow is locked into TensorRT-LLM and you need FP4 tensor cores, fine.

Everyone else should just buy the Mac Studio.

[ML @themachinescrew]

@TurnerNovak @TrungTPhan Just give it a snowblower

[ML @themachinescrew]

@nic_carter Shit take mate. We ain’t China.

[ML @themachinescrew]

@ErinnFL @MarioNawfal Bingo

[ML @themachinescrew]

@caprioleio Pffff no because its a shitcoin

[ML @themachinescrew]

@LarkDavis What am I forced to do lawk?

[ML @themachinescrew]

@RepJeffries You sir, are a patsy.

[ML @themachinescrew]

@TaikiMaeda2 Ya got me

[ML @themachinescrew]

@TrendingBitcoin It would be funny if he was just hitting a giant dab rig instead of the pen

[ML @themachinescrew]

@jnicolem Fake

[gino.eth 💽 @GinoTheGhost]

Jeffrey Epstein is Pedo Geppetto.

The new Epstein Files reveal he met with 4chan founder m00t the day /pol/ was created.

The modern alt-right is just a psyop.

[ML @themachinescrew]

@piovincenzo_ Poo poo pee pee listen to me

[ML @themachinescrew]

@Saboo_Shubham_ You’re telling me agents will train and get better 🤯??

[ML @themachinescrew]

@ripeth Ok but sir - the price.