31

I upgraded my PC, I have just upped the RAM to 64GB and got a Radeon 9700xt 16GB GPU.

I want to do some personal programming projects and was wondering what is the best model that would fit my HW?

I mostly use python, but dabble a little in go, and am interested in looking at rust.

I am running this on my desktop, the processor is a AMD 3700X (8c/16t).

all 21 comments
sorted by: hot top controversial new old
[-] kata1yst@sh.itjust.works 11 points 2 months ago

I'd recommend Qwen 2.5 Coder. Just try to ask very direct questions with smaller context.

QWQ is a bit stronger at more advanced coding tasks but I had a ton of trouble finding a version that would fit in my 24G 7900xtx.

[-] Smokeydope@lemmy.world 6 points 2 months ago

in your range 32b models work well give qwen coder a try

[-] badcodecat@lemux.minnix.dev 4 points 2 months ago

are you looking for autocomplete or chat?

[-] JamonBear@sh.itjust.works 3 points 2 months ago

Is there a different recommendation for autocomplete?

[-] badcodecat@lemux.minnix.dev 3 points 2 months ago

in general, you would want something fast (probably something that fits in your GPU/VRAM) so you can get suggestions as fast as you can type. for chat, you'll probably want the most intelligent/lorgest model you can run, it's likely fine if it's running on the CPU/RAM since the quality of an individual answer is more important than the speed in which many small answers can be generated. so, probably qwen for both, but, different sizes/quant for different use cases.

[-] absGeekNZ@lemmy.nz 2 points 2 months ago

chat to start with

[-] absGeekNZ@lemmy.nz 3 points 2 months ago

I'm running ollama 0.6.3 (pre-release) and rocm v6.10.5 on linux 6.11.0-21

Still getting

level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"

[-] Fisch@discuss.tchncs.de 2 points 2 months ago

I have an RX 6700 XT and I needed to change an environment variable to make it work. Maybe something similar is needed for you GPU. I'd try googling something like "RX 9700 XT ROCM" or "RX 9700 XT ROCM no compatible GPUs were discovered" if you haven't done that already.

[-] Smokeydope@lemmy.world 1 points 2 months ago* (last edited 2 months ago)

When I had my AMD GPU going the best way to get models running was kobold.cpp and using vulcan. The flag is like --usevulcan or something. Its way easier than getting a rocm fork working from source.

[-] ghost@feddit.org 3 points 2 months ago

As others have already mentioned, try qwen2.5-cider. With 16 GB, you should be able to confortably fit a quantised version of the 14b variant into VRAM. You can also try the 32b variant, but it will be much slower because not all layers can be off-loaded to the GPU.

[-] possiblylinux127@lemmy.zip 2 points 2 months ago* (last edited 2 months ago)

Deepseek r1 14b

Gemma (assuming you are ok with the license)

[-] wise_pancake@lemmy.ca 2 points 2 months ago

What's different about the Gemma license?

[-] possiblylinux127@lemmy.zip 3 points 2 months ago

Not foss

Although foss is debatable in a foss context.

[-] Boomkop3@reddthat.com 2 points 2 months ago

The one on top of your neck

[-] absGeekNZ@lemmy.nz 1 points 2 months ago

Update: After updating to the latest kernel (6.14), and removing the old amdgpu drivers that i manually installed. I am now running on my GPU. I'm running deepseek coder 33B, and it generates approx 6 words/second.

[-] massive_bereavement@fedia.io 1 points 1 month ago

what's that good looking gnome app?

[-] absGeekNZ@lemmy.nz 2 points 1 month ago

That is mission centre, a flatpak app. It is quite nice.

[-] icecreamtaco@lemmy.world -4 points 2 months ago

ChatGPT works great too if you don't want to use ram

[-] raldone01@lemmy.world 4 points 2 months ago

I am running local models only for privacy sensitive stuff. If you have ollama you can also setup openwebui and access both local and remote models through the same very nice interface! Also chatgpt API is much cheaper than subscribing.

this post was submitted on 28 Mar 2025
31 points (94.3% liked)

LocalLLaMA

2978 readers
38 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago
MODERATORS