Runing GLM-5.2 on local hardware(unsloth.ai) |
Runing GLM-5.2 on local hardware(unsloth.ai) |
https://unsloth.ai/docs/models/glm-5.2#usage-guide
In a prior thread, someone said it would take $500k in hardware:
NVFP4 at reasonable speeds (~120 tok/s) and concurrency is possible at a $80/90k figure with today's prices, maybe even less. That buys you 6 RTX 6000 PRO Blackwells, a decent CPU and motherboard, power supply. 576gb of VRAM.
You could do it for under $50k if you're OK with 40 tok/s decode, ~1200 tok/s prefill.
Each token has to read all the active weights. I think that's around 40B parameters active. At a 4-bit quant that's 20GB. With 100GB/s (replace with whatever your bandwidth is) and you get 5 tokens per second.
I feel like part of the reason for the relative stagnation in hardware over the last twenty years was simply the lack of use cases to justify hardware refreshes by businesses.
Most of the money and energy went to mobile for the last fifteen years.
Affordable local inference might be the gravy train the server, desktop, and laptop manufacturers need to get back in gear.
No, we're running into limits of moore's law, and it's showing in prices for new nodes, where they're getting denser but not cheaper.
On top of that, you will still be heavily quantized.
You can cluster these beasts too. Two and three (with two IP subnets) is fairly obvious. Four or more might need a switch depending on how much network latency affects things.
Apple seem to have forgotten about M series with gobs of RAM. I can't get the Apple shop to show more than 96GB of unified RAM and that costs a kidney.
If you are training and doing research it's great, if you want to cluster them it cant be beat, but if you just want local inference on a single box buy a mac or even a strix halo device.
(Still potentially very useful! But not magically ultra fast.)
Do the runes make it smarter or just run faster (or both)?
But I do like Unsloth Studio, quite a lot. It's nicely designed.
...a bit of an odd question: how well do LLMs losslessly compress, as in for cold storage?
I definitely don't have the hardware to run this model at any kind of reasonable speed (and I don't want to use a super aggressive quantization that would kill performance). Even so, I think it would be cool to retain an offline copy, in case... I don't really know, a solar flare destroys the internet some day, or maybe a zombie apocalypse. It would just be cool to have.
But 1.5 TB is a bit too much! If it could be compressed down into something semi kind of reasonable, that would be fun!
1. Reduce the number of parameters
2. Reduce the resolution of each parameter (quantization)
For 1, changing the architecture is typically only possible by the labs producing the models, which is why each OSS model release tends to feature a small number of carefully chosen model sizes (for example, Gemma4 comes in e2B, e4B, 12B, 26Ba4B, and 31B sizes).
Generally, models with higher parameter counts have more world knowledge. For coding models, this shows up as a stronger command of uncommon libraries/languages. Very small models (<20B) also lack “smarts.”
Reducing the resolution of each parameter is easier which is why lots of practitioners have their own quantizations, but this makes it harder for a model to “think” fluently. Interacting with heavily quantized models feels like interacting with someone who didn’t get any sleep the night before.
Models that have higher-fidelity quantization take more RAM and have higher “smarts,” but don’t necessarily have more world knowledge. Models with aggressive quantization tend to be more likely to make rookie mistakes, emit malformed tool calls, get stuck in loops, or even exhibit signs of “neuroticism” / “distress” in their thinking tokens.
Parameter counts = world knowledge, quantization = “smarts.”
This is a soft rule of thumb, the difference isn’t very strong.
Only a select few have the hardware required to run this to begin with, and even then the forecasted performance makes me wonder if it’s worth it at all.
The key to a model this large is (1) Use it to plan, generate lots of plan and farm out to a smaller model. Then for very specific and complicated portions precisely prompt for what you need.
I am very excited for local LLMs I think we may have GPT 5.5-xhigh level of performance for under 2000 EUR
This should put more pressure on the frontier models to avoid sitting on any fancy stuff and lower token prices as a whole.
Nothing beats a local LLM disconnected from the cloud.
LLM companies are valued as if they're going to have some enduring monopoly that they can extract money from... GLM-5.2 and similar models make that valuation very very questionable.
Alibaba released Qwen 3.6 "tiny" models not that long ago, they punch way above their weight(s)
I might build one for fun, but it's not going to change the economics alone. Still exciting it's possible.
For companies wanting LLMs in their products in general, I have to think going the local llm route is even more tempting. Somewhat dumb models are more than good enough for a lot of the things people are integrating LLMs into their products.
think Apple M6 or M7 with a currently unforeseen denser memory style, 256gb RAM
a couple inference or cache improvements on the algorithmic side, using less ram for context windows and doubling token speed again
denser open source models, packing more experts for smaller active layers
it'll still be expensive but like $8,000 - $13,000 instead of $450,000 worth of B200s
for $4k, you can get 20 months of claude max 200. i'd take claude over the hardware.
anthropic will have something to worry about when you can run a local model on your macbook that can code. but i think we're quite a ways off from that.
(I only ask Opus every 5 to 10 requests, when my local Qwen fails or when I encounter a situation that is too world-knowledge specific to be worth asking, but that way you can live easily with Claude's cheapest plan without ever facing usage limit).
The other way this could go is that Z.ai could decide to release a smaller model targeted towards coding. They've done that before (GLM-4.7-Flash had 30B params). It would be great if they decided to release something in the 80B-100B param range. Something that size would easily run in a current Strix Halo system.
guess we'll be paying $200/month for a while
We are maybe 10 years off that.
RAM prices are going to continue to increase for the next 2 years at least.
Even putting that aside it's currently around 40-70,000 EUR to run this with a FP8 quantization (which you need to get close to maximum performance).
To actually get GPT 5.5-xhigh performance in the real world you need more headroom to support things like subagents (which will fill up your KV cache).
I like local models but realism is important. The sweet spot for the next 3 years will continue to be ~35B MoE models. They might match GPT 5.5-xhigh for chat-style problems but not for coding.
Also I m not sure where you are getting the under 2k value. I bought a Framework desktop 128GB last year and my setup was around 2.7k. The same setup now sells for around 4.7k.
Do not mix the benchmark results of GLM 5.2 FP16/FP8 with FP4 or FP2.
* FP4 will mean a accuracy loss of about 3%. Not noticeable but more chance for mistakes.
* FP2 ... what is what most people are able to run at home, for a "reasonable" price. Your looking at over 17% loss in accuracy.
At that point, your running at less then claude-sonnet-4.6, as the issues compound with accuracy losses. And reasonable priced is still in the ~ $5000 range (192GB + GPU 32GB active/kv cache system).
For that price your using a Codex / Claude Pro subscription for the next 4+ years with better models (by default), let alone with a FP2 GLM 5.2 version. And your looking at < 10 fps. A MacStudio with 512GB will net you 18 a 20fps+ with FP4, but ... i mean, those used to be $10.000.
Unfortunately the local hardware cost is a major issue for running large models like that.
Edit: Its funny whenever the issue of cost and what you need to give up vs the subscription services, there are always people who downvote in bad faith.
i think your answer was perfect not sure why you are being downvoted
I’ve found that I need to go a couple steps past whatever quantizations are good enough in the KL-divergence testing to get good performance in real tasks with long context. So when Q4 is claimed to be lossless I end up with Q5 or Q6 for actual long-context tasks.
a lot of innovation occurring
True, Qwen3.6-27B is amazing for it's size. However, it seems likely that we're not going to see anymore of these smaller models from Alibaba/Qwen since several key players exited that organization a few months back.
In late 2027 or early 2028, Nvidia will release Vera Rubin DGX Spark, likely with double or better the performance of current Blackwell, though unclear if memory capacity will go up much from current 128GB. Two to four of those will run models like this decently.
In 2028 we should expect Vera Rubin RTX discrete lineup, including the replacement to the RTX PRO 6000. Likely memory spec will be minimum 128GB. Good chance of up to 200GB. Two to four of those will run NVFP4 models in this class very well.
No disagreement there, but it could easily last another 3 to 5 years which is a long time in tech terms.
Don't underestimate the markets ability to remain irrational
If making RAM and SSDs is now cause for a 10 figure valuation, after enough time somebody will dive in.
Having said that, I don’t think it’s all that tempting for companies at all, considering this whole market is developing rapidly and it’s nearly impossible to predict where we’ll be at in a year or two.
It's not like you'd lose capabilities, if anything this solution just gets better with time.
I think you’re better off renting GPU instances and running all the software on those. It’ll be cheaper than Anthropic and OpenRouter but slightly more expensive than electricity and depreciation of hardware.
For who pays for it, obviously the employer would.
For "how did I arrive at this number" Ballpark estimate from what I know about part cost. Most of that money will go towards AI cards about $5k for the mb, cpu, power supply, etc. $45k would be for as much ram and as big/expensive nVidia cards as you can get your hands on. The B300 has 288GB of VRAM in it. Probably what you'd be after.
I'm a Linux guy, but also don't always have alot of time. The Spark comes out of the box with a nice Linux distro that's pre-configured to be easy to setup and the guides and online resources make getting up and running trivial, for even some complex tasks. You would have to do a LOT of tinkering just to figure out some of the things the nvidia resources walk you through natively. They have guides for a ton of stuff that include the optimal settings so you don't have to figure it all out through trial and error.
Check out these "playbooks" for some examples. [0] There's a lot to be said for not having to piece all that together yourself.
https://build.nvidia.com/spark
I think between unboxing mine setting it up to run headless, and generating tokens was like 20 minutes total for me.
The spark can fine tune models in 1/4 the time and excels at other compute tasks in ways that Mac never can. Plus the high bandwidth ConnectX-7 ports would be like $1700 to buy on a card just for the network adapters... But for generating tokens, it just plain loses.
The number of parameters needed for these open weight models has mostly stabilized so the actual memory requirements aren't likely to change all that much.