alt Hacker NewsCan I run AI locally?
Comments
OP can you please make it not as dark and slightly larger. Super useful otherwise. Qwen 3.5 9B is going to get a lot of love out of this.
This seems to be estimating based on memory bandwidth / size of model, which is a really good estimate for dense models, but MoE models like GPT-OSS-20b don't involve the entire model for every token, so they can produce more tokens/second on the same hardware. GPT-OSS-20B has 3.6B active parameters, so it should perform similarly to a 3-4B dense model, while requiring enough VRAM to fit the whole 20B model.
(In terms of intelligence, they tend to score similarly to a dense model that's as big as the geometric mean of the full model size and the active parameters, i.e. for GPT-OSS-20B, it's roughly as smart as a sqrt(20b*3.6b) ≈ 8.5b dense model, but produces tokens 2x faster.)
This (+ llmfit) are great attempts, but I've been generally frustrated by how it feels so hard to find any sort of guidance about what I would expect to be the most straightforward/common question:
"What is the highest-quality model that I can run on my hardware, with tok/s greater than <x>, and context limit greater than <y>"
(My personal approach has just devolved into guess-and-check, which is time consuming.) When using TFA/llmfit, I am immediately skeptical because I already know that Qwen 3.5 27B Q6 @ 100k context works great on my machine, but it's buried behind relatively obsolete suggestions like the Qwen 2.5 series.
I'm assuming this is because the tok/s is much higher, but I don't really get much marginal utility out of tok/s speeds beyond ~50 t/s, and there's no way to sort results by quality.
Is it correct that there's zero improvement in performance between M4 (+Pro/Max) and M5 (+Pro/Max) the data looks identical. Also the memory does not seem to improve performance on larger models when I thought it would have?
Love the idea though!
EDIT: Okay the whole thing is nonsense and just some rough guesswork or asking an LLM to estimate the values. You should have real data (I'm sure people here can help) and put ESTIMATE next to any of the combinations you are guessing.
Cool thing!
A couple suggestions:
1. I have an M3 Ultra with 256GB of memory, but the options list only goes up to 192GB. The M3 Ultra supports up to 512GB. 2. It'd be great if I could flip this around and choose a model, and then see the performance for all the different processors. Would help making buying decisions!
This lacks a whole lot of mobile GPUs. It also does not understand that you can share CPU memory with the GPU, or perform various KV cache offloading strategies to work around memory limits.
It says I have an Arc 750 with 2 GB of shared RAM, because that's the GPU that renders my browser...but I actually have an RTX1000 Ada with 6 GB of GDDR6. It's kind of like an RTX 4050 (not listed in the dropdowns) with lower thermal limits. I also have 64 GB of LPDDR5 main memory.
It works - Qwen3 Coder Next, Devstral Small, Qwen3.5 4B, and others can run locally on my laptop in near real-time. They're not quite as good as the latest models, and I've tried some bigger ones (up to 24GB, it produces tokens about half as fast as I can type...which is disappointingly slow) that are slower but smarter.
But I don't run out of tokens.
Having the rating of how well the model will run for you is cool. I miss to also have some rating of the model capabilities (even if this is tricky). There are way too many to choose. And just looking at the parameter number or the used memory is not always a good indication of actual performance.
The RAM/VRAM cutoff matters more than the parameter count alone. A 13B model in Q4_K_M quantization fits in 8GB VRAM with reasonable throughput, but the same model in fp16 needs 26GB. Most calculators treat quantization as a footnote when it is actually the primary variable. The question is not "can I run 13B" but "what quantization level gives acceptable quality at my hardware ceiling".
Sorry if already been answered, but will there be a metric for latency aka time to first token?
Since I considered buying M3 Ultra and feel like it the most often discussed regarding using Apple hardware for runninh local LLMs. Where speed might be okay, but prompt processing can take ages.
[flagged]
[flagged]
[flagged]
i think the perplexity is more important than tokens per second. tokens per second is relatively useless in my opinion. there is nothing worse than getting bad results returned to you very quickly and confidently.
ive been working with quite a few open weight models for the last year and especially for things like images, models from 6 months would return garbage data quickly, but these days qwen 3.5 is incredible, even the 9b model.
This is kind of bogus since some of the S and A tier models are pretty useless for reasoning or tool calls and can’t run with any sizable system prompt… it seems to be solely based on tokens per second?
Open with multiple browsers (safari vs chrome) to get more "accurate + glanceable" rankings.
Its using WebGPU as a proxy to estimate system resource. Chrome tends to leverage as much resources (Compute + Memory) as the OS makes available. Safari tends to be more efficient.
Maybe this was obvious to everyone else. But its worth re-iterating for those of us skimmers of HN :)
This is awesome, it would be great to cross reference some intelligence benchmarks so that I can understand the trade off between RAM consumption, token rate and how good the model is
Useful tool, although some of the dark grey text is dark that I had to squint to make it out against the background.
Finally! I've been waiting for something like this.
You can still run larger MoE models using expert weight off-loading to the CPU for token generation. They are by and large useable, I get ~50 toks/second on a kimi linear 48B (3B active) model on a potato PC + a 3090
This feels a bit pessimistic. Qwen 3.5 35B-A3B runs at 38 t/s tg with llama.cpp (mmap enabled) on my Radeon 6800 XT.
For some reason it doesn't react to changing the RAM amount in the combo box at the top. If I open this on my Ryzen AI Max 395+ with 32 GB of unified memory, it thinks nothing will fit because I've set it up to reserve 512MB of RAM for the GPU.
The M4 Ultra doesn't exist and there is more credible rumors for an M5 Ultra. I wouldn't put a projection like that without highlighting that this processor doesn't exist yet.
It would be great if something like this was built into ollama, so you could easily list available models based on your current hardware setup, from the CLI.
Literally made the same app, 2 weeks back - https://news.ycombinator.com/item?id=47171499
This doesn't look accurate to me. I have an RX9070 and I've been messing around with Qwen 3.5 35B-A3B. According to this site I can't even run it, yet I'm getting 32tok/s ^.-
When running models on my phone - either through the web browser or via an app - is there any chance it uses the phone's NPU, or will these be GPU only?
I don't really understand how the interface to the NPU chip looks from the perspective of a non-system caller, if it exists at all. This is a Samsung device but I am wondering about the general principle.
I don't see my beloved 5060ti. looks great though
Missing laptop versions of all these chips.
Has anyone actually built anything with this tool?
The website says that code export is not working yet.
That’s a very strange way to advertise yourself.
tbh i stopped caring about "can i run X locally" a while ago. for anything where quality matters (scripting, code, complex reasoning) the local models are just not there yet compared to API. where local shines is specific narrow tasks - TTS, embeddings, whisper for STT, stuff like that. trying to run a 70b model at 3 tok/s on your gaming GPU when you could just hit an API for like $0.002/req feels like a weird flex IMO
It says "RAM - unknown", but doesn't give me an option to specify how much RAM I have. Why?
Raspberry pi? Say 4B with 4GB of ram.
I also want to run vision like Yocto and basic LLM with TTS/STT
This is great, I've been trying to figure this stuff out recently.
One thing I do wonder is what sort of solutions there are for running your own model, but using it from a different machine. I don't necessarily want to run the model on the machine I'm also working from.
Missing RTX A4000 20GB from the GPU list.
Missing 5060 Ti 16GB
Missing the A18 Neo! :)
This just reminded me of this https://www.systemrequirementslab.com/cyri.
Not sure if it still works.
For me the "can run" filter says "S/A/B" but lists S, A, B, and C and the "tight fit" filter says "C/D" but lists F.
Just FYI.
What is this S/A/B/C/etc. ranking? Is anyone else using it?
Cool website. The one that I'd really like to see there is the RTX 6000 Pro Blackwell 96 GB, though.
Why isn't there some kind of benchmark score in the list?
Is there a reliable guide somewhere to setting up local AI for coding (please don’t say ‘just Google it’ - that just results in a morass of AI slop/SEO pages with out of date, non-self-consistent, incorrect or impossible instructions).
I’d like to be able to use a local model (which one?) to power Copilot in vscode, and run coding agent(s) (not general purpose OpenClaw-like agents) on my M2 MacBook. I know it’ll be slow.
I suspect this is actually fairly easy to set up - if you know how.
This does not seem accurate based on my recently received M5 Max 128GB MBP. I think there's some estimates/guesswork involved, and it's also discounting that you can move the memory divider on Unified Memory devices like Apple Silicon and AMD AI Max 395+.
Nice UI, but crap data, probably llm generated.
awesome, needed this
Oh how cool. Always wanted to have a tool like this.
I have spent a HUGE amount of time the last two years experimenting with local models.
A few lessons learned:
1. small models like the new qwen3.5:9b can be fantastic for local tool use, information extraction, and many other embedded applications.
2. For coding tools, just use Google Antigravity and gemini-cli, or, Anthropic Claude, or...
Now to be clear, I have spent perhaps 100 hours in the last year configuring local models for coding using Emacs, Claude Code (configured for local), etc. However, I am retired and this time was a lot of fun for me: lot's of efforts trying to maximize local only results. I don't recommend it for others.
I do recommend getting very good at using embedded local models in small practical applications. Sweet spot.