I play with local LLMs a lot. I've spent more on hardware than I should. I'm friends with a local group of people who have spent a lot more than I have.

The warning I would have for everyone is to temper your expectations and read the fine print carefully. The big build in article starts off with a $40K budget and then includes 4 GPUs that are $12K each. For those doing the math, this build is going to cost more like 50-55K.

Local setups also often rely on quantization and techniques like REAP to fit the models on their hardware. You will read a lot of claims that 4-bit quantization is lossless, but those claims come from KL divergence measurements on a small corpus. Use one of these 4-bit models on long context coding tasks and the quality will be noticeably less. Even for non-coding tasks like dataset analysis, I can measure a substantial quality difference between 4-bit models, 8-bit quants, and even some times the full 16-bit source.

This article is also encouraging the use of a REAP model, which means someone has cut out some of the weights to make it smaller. The idea is to remove weights that are less useful for certain tasks, but again this is going to reduce the overall quality of the output.

The trap is that people say "I'm running GLM-5.2 locally!" and it sounds amazing when you look at the GLM-5.2 benchmarks. However they're not actually running GLM-5.2, they're running a model derived from GLM-5.2 that discards most of the bits and drops some of the experts. It does not perform the same as what you see in the benchmarks. In my experience, the divergence between a quantized/REAP model and the parent model is unnoticeable when you try it on very small tasks or chat, but becomes painful when you start trying to use it on long-horizon tasks where little errors start compounding.

Then you get into the slippery slope of thinking you're $50K deep into this project, but what you really need is just one or two more of those $12K GPUs to use the next level of quantization that might improve the quality a little more and make your investment worthwhile...

For qwen3.6-27b you can also run the q4 variant with full ~250K context on one 3090. It's fast enough to not be frustrating so the speed gains with 2x 3090s wouldn't be worth it to me. Running a q6 on 2x 3090s at half the speed with a smaller context is an option, but you're really not going to compete with SOTA models there anyway so unless you already have 2x 3090s, I would say 1 is the best investment given current prices. It's good enough to do a lot, especially with a well-configured harness.

"A great way to go is 2x RTX 3090s for a total of 48GB VRAM total. You can then run Qwen3.6-27B, which is an awesome model."

Just want to note that for $3k you can get an M5 macbook pro with 48gb of shared memory, and it will not be a giant box. Also, consider committing to spending that money on a cloud hosting provider, which will be at least somewhat cheaper if not significantly cheaper. It is awesome being able to run models locally though.

I am somewhere in the middle, where I want something with more than 48GB/$2k of VRAM, but less than 384GB/$40k.

I'm curious if GMKtec's EVO-X2, with ~96GB of usable VRAM, is still a good solution for something like this for $3,399.

>$40k gets you almost-Opus

GLM 5.2 is "almost Opus," and it needs at least 8xH200s for comfortable inference (so it's closer to $400k than $40k).

They suggest using this modified model:

>A REAP-pruned (≈22% of experts removed), Int8-mix NVFP4 quantized version of GLM-5.2, ≈594B parameters.

I wonder how it behaves in practice outside of benchmarks. Qwen3.6, even at 6-bit quantization, often gets stuck in loops while reasoning. And here they've also removed some experts. I mean, sometimes an 8-bit or 16-bit small model can be smarter than a lobotomized large model. I heard the consensus is you shouldn't go below 8 bit for coding.

Also, it's not clear what is left of the available context when you try to fit a lobotomized model into 4 RTX 6000s. Anything below 100k is barely usable because it often hits compaction before it's able to gather the necessary context P.S. found in the repos, 240k context

You can get amazing local STT using parakeet which can use as little as 600mb of vram. Better or as good as whisper v3 large

I agree that local LLMs are the likely future and worth investing in… but at $40k for possible-SOTA right now, this isn’t worth it for the average consumer.

I’m pretty bullish that Apple will deliver something very competitive for the average consumer in the next couple years.

Apple M series chips deserve a mention as another option, especially since you get a whole Mac laptop or desktop workstation too.

They have unified memory and respectable inference performance, and for some variations can be cheaper than video cards, especially if you get an older-gen high-end M series with a lot of RAM used or refurbished.

I've read that Apple has plans once the RAM bottleneck passes to offer more RAM in all their models, and that future M series GPUs and NPUs will be even better for local inference, so in the future I expect Apple to be a serious offering for local inference and AI research workstations.

And what about AMD and Intel Arc GPUs? They don't get as much love but I've heard they can be compelling for certain shapes of a local LLM configuration.

At this point though, I think we may be in a "renters market" for LLM compute. If you want privacy it might be better to rent GPU time in raw form or use spot pricing at various providers. It probably only makes sense to build if you have extreme privacy/security needs or just want to do it cause it's cool.

did he call Qwen a SOTA model?