Something to handle code, text and math.
Specs for what?
The hardware you run it on will have a range of specs.
The model you try to use will have a bunch of measurements that can be called specs.
Once you pick some hardware, the measurements of the model you run on it can be adjusted for “accuracy” or speed.
Of course, the range of hardware that’s available to you informs that calculus.
The alternative to answering this post is to get a Mac mini or whatever they’re selling as a desktop llm device now and not mess around.
16 GB VRAM GPU, models stored on SSD, rest of the computer doesn’t have to be crazy. Intel Arc is best bang for the buck at the moment. You can get LLM running on 8 GB cards or even the CPU, but IMO such small models are more novelties than workhorses. I personally use Debian but you’ll be fine as long as your distro’s repo has drivers recent enough for your GPU.
For perspective, I’m using such a build to help with boilerplate code, single-use scripts that I don’t have the patience to trial-and-error (like ones that have to deal with directory structures and special characters), getting an idea of what’s what when decompiling and reverse engineering, brainstorming tip-of-the-tongue ideas, and upscaling images.
heavily depends on the model and quantization level
choose the model you want on this website and it’ll give you some specs likely to run it
any/most distros will do, especially if you run it on Docker
if you’re going with intel cards (best $ per GB VRAM right now), you could get a decent machine under $3k
I use local LLM with 8gb VRAM and 32gb system RAM, thanks to Vulkan support. My GPU is a RX 7600. I can run
qwen/qwen3.6-35B-A3B-Q4_K_M.ggufandgemma-4-26B-A4B-it-Q4_K_M.ggufin example. It will first fill in the GPU and the rest will use the system RAM instead, which is slower but at least it will fit and run bigger models. I just need to lower the context length, which has a great impact (current custom value is 64k for anyone who wants to know).But this is still highly limited and not competitive at all. I mostly play around with it and occasionally ask a question here or there and that’s it. So if you are serious about your system, you need something faster and with more than just 8gb VRAM.
As a side note, Qwen3.6-27B is much more capable than Qwen3.6-35B, even though it is much slower.
https://huggingface.co/unsloth/Qwen3.6-27B-GGUF
For coding tasks where you don’t mind waiting, you should be able to barely squeeze in the 8-bit quantized version with 32 GB RAM + 8 GB VRAM and have a pretty competent local model. 4-bit quants work but they have issues with complex tool calls.
If you use the MTP branch of llama.cpp (and a suitable model) you can even double or triple your token generation speed: https://github.com/ggml-org/llama.cpp/pull/22673
For easier tasks, disable reasoning for instant responses.
Get a 3090
