Show HN: Getting GLM 5.2 running on my slow computer
github.com345 points by vforno 17 hours ago
345 points by vforno 17 hours ago
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me.
But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility.
I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context. How it responds in int4 and whether the quality is maintained or not. Until I got to the point, on my computer with 32GB of RAM, I was able to communicate with GLM 5.2 with times that, of course, aren't high in cold start, but even then, we're talking about 0.1 tok/s, but that wasn't important to me. The important thing was the journey to reach this goal. I just wanted it to work at all costs, even slowly.
So I created Colibrì, which was born from a very simple idea, to be honest, but tested in every way, where a 744B Mixture-of-Experts model activates only ~40B parameters per token—and only ~11 GB of those change from token to token (the routed experts). So:
The dense part (attention, shared experts, embeddings—~17B params) stays resident in RAM at int4 (~9.9 GB); The 21,504 routed experts (75 MoE layers × 256 experts + the MTP head, ~19 MB each at int4) live on disk (~370 GB) and are streamed on demand, with a per-layer LRU cache, an optional pinned hot-store, and the OS page cache as a free L2.
The engine is a single C file (c/glm.c, ~1,300 lines) plus small headers. No BLAS, no Python at runtime, no GPU.No GPU or serious hardware because I don't have that hardware so I can't test it on hardware that is more powerful than my computer.Colibrì is a one-person project, written and tested entirely on a 12-core laptop with 25 GB of RAM — the numbers above are the ceiling of what I can measure at home.
Any feedback is welcome! (and if anyone wanted to participate in the project I would be delighted)
Repo: https://github.com/JustVugg/colibri
My main question is whether when put into practical use, this can be measured in tokens/second, or more like 1 token per minute... I have seen locally hosted LLM that are as slow as 1 tok/second still be very useful if you give it a project to do something overnight and metaphorically walk away from it, check back with what it has done in 6 or 8 hours. 0.05 to 0.1 tok/s on the other hand, as reported in the URL for the lowest class of hardware, isn't really usable for much. edit: I think this is a fantastic project in general concept, and look forward to seeing more efforts towards the general idea of being able to run a 350B to 900B size model locally, even if as slow as 1 tok/s, on hardware that ordinary people can afford. Anything along the general concept of "we have fast read NVME SSD storage, we have a big ass model on local disk, we'll read it at 11GB/tok as we need it, not try to load the whole thing". The funny thing is Claude Cowork has taught me to be patient with response timelines. I’m now figuring I’ll be running locally no later than 2028. (I want to spend no more than $10k. And I want to run a model comparable to today’s SOTA.) I’ve been wondering if chat is the wrong interface for slower local models (and some projects) and maybe something like a ticket system is a better fit. I just decided how I would test this idea on my available hardware before I go drop money on a Mac Studio or GPUs. I’ll probably have a POC this week. There is nothing novel here, just need to spend the time to get it working for me. Having a thin python/ts orchestrator and workers that pick up tasks from the directories like events and decide whether to make deterministic calls and wait is pretty standard albeit custom way of doing things in this space where you're bottlenecked by the concurrent call your workers/agents can make. The hard thing is always keeping complexity low and being ZeroOps. In the readme you can see benchmark which everyone with different hardware is running Colibrì, and I have to say I've seen great times! I'm always doing more to improve! I have a 16-core system with 256GB RAM here I could try it with but regretfully it's so old the CPUs aren't AVX2 capable. Otherwise it makes a fairly good llama-server test system for CPU only stuff. Oh well. Time to upgrade (painful to the wallet these days). Maybe we can see some integration! If you get good at extracting remarkable performance from the most lesser of instruments enough to pull their own weight regardless, just imagine what it can be like when such a practitioner gets behind the keyboard of a world-class Steinway. And just does what they do best. Without ever having touched such a capable instrument themself. On a level playing field the expression of virtuosity can outshine those who have never known any instrumental limitations at all :) When pulling way more than your own weight happens like for few others. There should be an award for getting the most out of the electronics rather than trying to reach orbit by building the tallest pile of e-waste. First Prize right before your eyes ! Grande praise ! And just starting to ascend toward an unconquered summit that others find forbidding ;) Or they find uninteresting since the limit naturally lies on firm earth somewhere below the stratosphere. For most projects the more practical solution is to use clouds offering GLM 5.2 for free. 1 token per minute is minuscule compared to their rate limits for free usage. > on hardware that ordinary people can afford These days, can "ordinary people" afford 24GB of ram and half a TB of NVME ssd? sigh The very boring pair of two 16GB ddr5 6000 I had in my newegg shopping cart went from $399 to $475, so increasingly the answer will be "no". Maybe that's a measure of the self-fulfilling dollar incentive toward "renting" someone else's RAM in the future rather than trying to actually own such an outlandishly luxury item :\ Ideally this engineer's approach will yield better performance on lesser equipment in the future, if they keep up the good work after they get more-capable gear to experiment with as time goes by :) Working on something similar targeting macOS on Apple Silicon, Unsloth split GGUF, compressed partial residency in unified memory (would make more sense on 128GB instead of my 64GB...), native Metal kernels, and RAM-only native compressed KV. Happy to put on GitHub when it's ready. I was actually just working on the same thing as this, but I went down the route of mmapping the entire model into memory to avoid the extra ram usage. I also had Claude implement Medusa[1] on the model to try and avoid loading an additional model into memory but still get the benefits of MTP. Currently at a stop light so I can't list everything and I didn't get to read your full post either yet. To expand since I just got home, I'm making all of my modifications to llama.cpp, the goal was to eventually put this on a SBC of some kind with an nvme to handle the mmapped files. I think the theoretical limit of my current setup is about 1.8 tok/s based on prior testing but that is also with the additional medusa heads not fully trained (I honestly don't know if the counting it's generated tokens or not.) In the end it seems like the idea we had is similar, I just don't know how to write an llm parser/runner from scratch yet and instead of specifying what needed to stay in memory I just let the linux kernel handle it. Oh last note, I also capped llama.cpp usage to 16GB of my 32GB, so it might be possible to get it down even lower. if you like, colibrì always needs to improve so if you have ideas or anything else you are welcome for pull request issues and also benchmarks! Yeah I'll see what I can transfer over from my llama.cpp work. As before I'm not too experienced with llm work, but I have a lot of experiments I'm trying out. So I'll make a PR if I get any interesting results. Pretty cool! I've also been playing around with GLM 5.2 this week and was equally impressed. At work we're running it locally on some crazy expensive hardware as a test before starting another project so it's great to see people taking this massive FOSS model release and running it on an average machine, even if it's not terribly practical at this point. Nice work! The page has an SSD wear warning [0] I use desktop PCs that I build from components so I can replace the SSD, but what do users with soldered SSD do? Just avoid these applications or forge ahead disregarding the possible early burnout of their storage? They must use external storage as the burner SSD. Yes, avoid. Laptops with soldered in SSDs should definitely monitor their usage and take care with this. This project seems more of an experiment than something everyone should run, but pretty cool nonetheless It's a very conservative warning. The application does not perform writes, so the application doesn't actually wear your SSD at all. The rest is just application-independent general hygiene. From what I understand, the warning is about swap-out during heavy memory use. You don't need to be superstitious here: disk activity, including writes in particular, can be measured. E.g. `iostat` or `vmstat` on Linux. AppleCare. Even under AppleCare this is a $400 service which for an older macbook costs almost as much as the whole thing. And without Applecare it's not worth fixing at all. I've taken a similar strategy w/ image/video gen at https://github.com/cretz/thinfer (see video branch for a ton of work). Basically I kept needing an inference engine that could stream weights in and out as needed in an LRU manner. So I ended up vibe coding this thing that accepts a `--vram-budget` and stays under it (mostly). It turns out moving mmap'd bytes in and out of VRAM is way cheap compared to compute. Coupled with some pipelining/double-buffering, I almost always end up compute bound not memory bound. Granted I use way smaller models heh. Wow, I see you managed to fit in so many models (krea, wan, hunyan, etc.). Did you get to build a common harness to run all of them? Which ones stay under your VRAM budget more consistently? All stay under because I had Claude build the workflow to respect it (text encoding, denoising, vae, etc), there's just a tiny bit of untracked pieces. While there are common interfaces to invoke them (CLI and API/webpage) and they share ops and some pieces, lots of model logic is unique. This is all vibe coded and surely has inaccuracies. This sort of thing is a lot of fun. I've been going smaller.. I have a custom-quantized Rust port of DiffusionGemma (26B) that seems to perform better (in responses) than benchmarks seemed to indicate and reasonably fast for its model size. Works really well on a 36GB mac as well for both prefill and generation. It's been interesting learning about the balance of factors for performant metal kernels on unified memory. Should have a repo up on github in the next few weeks. Is this similar to fastllm? fastllm targets the GPU, while colibri uses CPU inference only I'd be curious about an.option that would allow glm use with a low end GPU like a 2080 ti... I just learned about Gemma4.pas at the beginning of this week. Now this. This make me wonder how can inference engines could be built that easy. I'm not knowledgeable in this, but I thought it would take very deep Mathematic and system level knowledge, ... and a lot of patience. How much time is spent interfacing between userland and the kernel? Can you try to get it to run as a kernel module? :) Also in case your CPU is old enough, did you try disabling CPU bug mitigations? This is something that would benefit from Intel Optane memory. Too bad it was killed at the time. Curious for what an MTP only result would look like, both in terms of output quality & tk/s ?! I love it but where do you find that NVMe SSD for less than the price of an h100 fan let alone the memory I'm not fully understanding this business of MoE so please forgive me if this is a dumb question, but would it be possible to use MPI with a small cluster to distribute the load? It’s a good question. In theory MPI could distribute experts across nodes. In practice, for small clusters the added network latency usually hurts more than it helps. Better suited for big clusters with fast interconnects. For now we're focusing on single-machine speed (caching, GPU hybrid, etc.). I am curious if it's possible to adjust this to use more RAM, as i've got a machine with 64GB RAM and 24GB VRAM. Or perhaps I could run Gemma/Qwen on the GPU and have GLM-5.2 delegate smaller tasks to it. It might take some retraining of GLM-5.2 I'm also curious if you can speed this up by using many disks in parallel to increase bandwidth. >SSD Wear Warning > Cold starts are heavy on random reads (~11 GB/token). Reads themselves are safe, but the OS page cache can generate writes. Heavy use may accelerate wear on cheaper SSDs. Use with caution and monitor your drive health. Hmm, maybe a safe way to do this would be to make a separate partition for the model weights, and set them to read-only?
Not sure how the page cache works, if it's like per partition or per disk. If it's per disk, maybe you could have a read-only data.iso formatted as a partition and mount it as a disk? I have a small laptop.
If you have more disks available, you could really do some testing.
When you have some benchmarks, submit a pull request or issue so we can maybe work on them.
We are really happy for contribute! I have epyc 9654 ES and a 7900 XTX. I was running the numbers, and even if I maxxed out the ram to like 12x32 gig sticks, it would cost me thousands more and I could only run GLM-5.2 at a couple tokens per second at q3. So this project is very promising because it suggests I could get pretty high speed and this CPU/motherboard combination suggests I have a lot of pci bandwidth that is unused. I think another route might be looking at holding an even larger chunk of model weights in ram, and taking advantage of RAM<->GPU bandwidth, perhaps using a PCIe 5 GPU. This was my first thought since I have dedicated GPU. If you are using Laptop, you're looking at shared memory between the iGPU and CPU. I've also tried that route, but I have always been skeptical of killing flash with too many reads, it essentially uses SSD like it's a consumable item. I'm going to benchmark this right now with what I have and I'll get back to you on github. > OS page cache can generate writes Is this a hallucination? What am I missing? Why would heavy reads generate writes? Good catch! Disk reads do generate writes to cache. But the cache itself is in RAM, not on disk. So it shouldn’t cause additional wear of SSD. > Is this a hallucination? What am I missing? Why would heavy reads generate writes? I take it heavy reads means more stuff goes into RAM, meaning other stuff has to be cached? I've got same question as GP: e.g. is there a way to set moderately fast consumer NVMe SSDs (I've got both a Samsung 990 Pro and a WD SN850X) in a complete read-only mode to prevent "wear"? Spilling Wouldn’t turning off swap fix this issue? Better to just change swapiness? https://askubuntu.com/questions/103915/how-do-i-configure-sw... I wonder how would a RAID0 array of either disks or even nvme improve the performance of this. I wonder if you could replicate this in a Colourful GeForce RTX 50-series GPU, they ship it with 2 NVMe drive slots. I'd love to! Right now I only have a very consumer-grade computer that I've had fun with! We'll see! Question to the OP, have you tested this on a machine where the entire model and context fit in RAM ? I think if you had something like a theoretical used/refurb 2U rackmount server with two older multi core CPUs, 768GB of RAM, you would see faster performance loading a Q6 or Q8 GGUF of GLM5.2 into a freshly-compiled latest copy of llama-server, with the "no-mmap" option turned on to intentionally load the whole thing into RAM at the time the llama-server daemon launches. If you want a CPU-only machine with 512GB to 1024GB of RAM, despite extreme cost rises, there are still some great options out there from companies selling ex-lease stuff that's 3, 4, 5 years old. It'll be loud as hell under full CPU load when running inference, so if you plan to use it at home, put it in your garage or basement or laundry room or somewhere similar on the far end of a network cable. The software that OP has published appears to be specifically designed to hold only the active parameters in RAM (<100GB) and read content off local NVME SSD as needed on the fly. All that NVME SSD read wouldn't be necessary if you can hold the model in RAM, even in the absence of any GPUs. Another recent project that runs a huge model on a 48gb Mac is https://github.com/danveloper/flash-moe - it gets over 5 tokens/sec on an M3 Max compared to this projects very impressive 1 token/sec on an M5 Max. So for anyone wanting to tackle a Mac only version that targets lower spec machines this looks like a good candidate with plenty of room for speedups [edit: because it doesn't use the gpu]. Not hijacking anything as this project is amazing. Would this cause issues with SSD lifespan? What causes problems is the rewriting in this case are only read while writing is the cache! However, I'm working to improve more and more and make some parts lighter! You can keep the KV cache in (possibly Unified) RAM to avoid SSD writes entirely. Not sure if it would fit on a 32GB laptop, though. Is it possible to run this into an agent? pi, claude code, etc..? I've only tried it with LM studio, but i'm guessing this is a bit different We're working on it right now with a pull request that will also arrive for opencode! This is great, well done! I love seeing people run things where they weren't meant to be run. related and possibly more general purpose https://github.com/t8/hypura With so many people implementing their own SSD streaming for specific combinations of model+hardware, maybe we should look into upstreaming to antirez/ds4 or llama.cpp...
walrus01 - 4 hours ago
JumpCrisscross - 29 minutes ago
codazoda - 2 hours ago
alexhans - 36 minutes ago
vforno - 4 hours ago
walrus01 - 4 hours ago
vforno - 4 hours ago
fuzzfactor - an hour ago
charcircuit - 2 hours ago
bigiain - 2 hours ago
walrus01 - an hour ago
fuzzfactor - an hour ago
fuzzfactor - an hour ago
Archit3ch - 2 hours ago
Cieric - 3 hours ago
vforno - 3 hours ago
Cieric - an hour ago
shrinks99 - 4 hours ago
voidmain0001 - 2 hours ago
hoppp - 2 hours ago
cjbprime - 41 minutes ago
killerstorm - 2 hours ago
Cider9986 - 2 hours ago
Gigachad - 2 hours ago
kodablah - 3 hours ago
espetro - 2 hours ago
kodablah - 2 hours ago
mmastrac - an hour ago
nogajun - an hour ago
vikmals - 37 minutes ago
aliljet - 13 minutes ago
sakesun - an hour ago
qiqitori - an hour ago
xtracto - 2 hours ago
flockonus - an hour ago
tannertech - 2 hours ago
bobim - 4 hours ago
vforno - 3 hours ago
tarpitt - 3 hours ago
vforno - 2 hours ago
tarpitt - 2 hours ago
valicord - 2 hours ago
fallingbananna - 2 hours ago
TacticalCoder - 2 hours ago
onlyrealcuzzo - 2 hours ago
gcr - 2 hours ago
throwa356262 - 2 hours ago
xtracto - 2 hours ago
mariopt - 4 hours ago
vforno - 4 hours ago
xfalcox - 4 hours ago
walrus01 - 4 hours ago
bahmboo - 2 hours ago
Pragmata - 4 hours ago
vforno - 4 hours ago
Archit3ch - 2 hours ago
Pragmata - 3 hours ago
vforno - 2 hours ago
stavros - 3 hours ago
khimaros - 2 hours ago
Archit3ch - 2 hours ago