I just bought a used Ayaneo 2 handheld, it has an old(er) mobile RDNA 2 GPU and I was blown away by how well this thing performed under Linux. Almost everything (that's not a recent AAA game) runs beautiful and a lot faster/smoother than it does under Windows. The experience has been so good that I'm considering switching my main pc (with a 9070XT) to Linux as well.
No doubt Timur contributed heavily to this given Valves Steamdeck (which uses a very similar but slower GPU).
Given the current hardware prices it's pretty awesome to see someone squeezing maximum performance out of old hardware!
I'm sure Valve probably still deserves the credit, since the Steam Deck uses a RDNA 2 gpu, but the article mentions that Timur specifically worked on gcn1.0 GPUs - e.g. radeon HD 7800/7900 from 2012 (!)
Those are pretty old but Im sure there are reasons. Valve has access to specs from their consumers through steam so maybe a large segment of the third world uses old GPUs for gaming.
My experience has been that for Linux you are always better buying older mid tier hardware because all of the issues and optimisations have already been worked out and those changes have flowed through to your distro so you aren’t waiting on kernel updates.
> those changes have flowed through to your distro so you aren’t waiting on kernel updates
Unless you insist on running a server distro that's consistently obsolete by design (and if the notion of GPU comes into picture, that definitely shouldn't be the case), it shouldn't matter in practice. Every reputable desktop distro has a kernel/mesa stack that's up to date.
I've switched my gaming PC last year to Linux and it's been flawless.
Originally ran a 3070 which matches your "older mid tier" description and then upgraded to a 9070XT maybe 6 months after launch so not so old or mid-tier.
I switched to Bazzite about 3 weeks ago and am amazed at how well everything "just works". Steam and Battlenet games all running. Nvidia 5070, AMD Rizen 7800x3d, recent gigabyte motherboard.
My gaming PC has a 9070 non-XT, runs Linux, and runs all but a small handful of games [0] just fine. I suspect you'll be happy with the switch.
I run games both new and old and one of my favorite guilty pleasures is looking at the Steam forum for a four, eight, or ten year old game that I've started playing because it has recently become popular again and reading the complaints from Windows users about how a driver update screwed up the game... whether because of glitchy or incorrect graphics or unavoidable crashes. Meanwhile, I'm cruising along on Proton with zero issues. :smug-face:
[0] ...that small handful includes those that go out of their way to be incompatible with Proton...
Yeah AI is extremely good at reverse engineering compared to humans. It's one of those things were there's a huge amount of tedious but not super complex work. I think if you can set up a good harness for the agent it can probably write complete drivers.
The most difficult part is likely that a lot of hardware is easily brickable if you do the wrong thing, so I'm not going to let it loose on e.g. my solar inverter.. even though their software is shit and I'd love to replace it. (Don't buy QCells.)
I got a r9 285 in 2020 something while the crypto frenzy was still eating up all the gpus. It was 6 years old, got it for like 60 bucks if I remember correctly, best purchase ever, I got to play gta V at 60fps again.
Try to remember back to 2015 the graphics were not that bad. 4k performance was poor but for 1080p 60fps on pretty much anything.
4K is kind of pointless for gaming anyway, IMO. I've got a 32" 4K 165 Hz OLED screen and I much prefer 1080p at 165 Hz over 4K at <= 60 Hz and a pegged GPU. I don't really see pixels either way. 4K is nice for text, though!
Use as a dedicated GPU for encoding and decoding video.
Post processing like frame interpolation or superresolution. Use for GPGPU workloads. Run additional monitors independently. Use for GPU passthrough to virtual machines. Use as a backup GPU for troubleshooting. Use for test code without breaking the main GPU
For video decode if it supports the codec you want you're set, but video encode has definitely improved on more modern GPUs. Older GPUs work but you'll likely get worse quality for a given bitrate.
One thing they should've learned from Nvidia is that it's really worth it for them to invest making their devices function as broadly as possible. Crypto and AI waves both benefited Nvidia much more than AMD partly due to their devices being more universally usable.
That "partly" was worth hundreds of billions of dollars but AMD were cheap/shortsighted enough to hire a few dedicated engineers.
I now have a 2011 or 2012+ 27" iMac everywhere I need a computer, running Linux Mint Mate, and it works better and with less frustration that any new $2500+ Lenovo workstation laptop my employers give me.
Honestly, the folks writing inference drivers for Llama.cpp / GGML would sort of benefit from better compiler work like this.
In general, Valve's work has been exceptional and supplementing AMD's own ROCM/OpenCL and Vulkan team, they've gotten a lot of defaults right and people should work together with Valve to improve support for their chips.
I have a Radeon RX 6900 XT (16 GB VRAM, originally released in 2021), and it's possible to run some lightweight models to have okayish performance and quality of output, but nothing I've tried has come anywhere close to the quality even of the models I can use for free from OpenCode Zen or the free tier of Openrouter. If you want to keep everything local on the same card I have, it requires putting up with a model that's noticeably worse in virtually every metric than what you can get for free elsewhere, and the GPUs this article are talking about are three times as old as mine.
It would be awesome if someone manages to figure out how to get small enough models to fit on older cards to be viable, but I'm not optimistic that it will come without some sort of fundamental architectural innovation rather than incremental improvements, and it's not clear if and when that will happen.
I think you could replicate this with a larger model on your device.
Overall with the right quantisations for both the model and KV cache you can get a lot of mileage out of this old hardware. Speed remains the main limitation, as IIRC I was getting ~26-30tps on a 7700S.
With an extra 8gb of vram you could run qwen 3.8 27b pretty comfortably, which isn't quite as good as frontier models but definitely on par with free models on openrouter and whatnot.
Also you can use multiple GPUs at once, two of your GPUs could run qwen 27b very comfortably, and with great performance.
Most of these older cards are lacking the physical hardware for fp8 or other lower precisions that most quantized models use. Or the memory to run models at higher precision.
Assuming Valve funds this work, just buy their products. If possible, avoiding credit cards as the CC companies are trying to dictate policies about which games are acceptable and which aren't. I buy the occasional steam card with cash. I encourage everyone to shift a bit of their spending away from CC's in order to reduce the power of these companies to tell us how to live our own lives.
I understand the good will of the intent but... you have to understand that those driver code paths went thru massive QA over the years. On such complexe hardware, any modifications, even believed benign, can be disastrous for some/many software actually still 'in production'.
This is very risky: one guy QA over a massive amount of software with hardly a few remaining users able to report issues of with those GPUs...
Better have a slow working well tested driver, rather than a broken driver which is supposed to be faster...
That is a valid concern in theory, but in practice, improvements to drivers for old GPUs rarely break things. There are regression tests... and part of it might be Timor being very diligent in his work.
I just bought a used Ayaneo 2 handheld, it has an old(er) mobile RDNA 2 GPU and I was blown away by how well this thing performed under Linux. Almost everything (that's not a recent AAA game) runs beautiful and a lot faster/smoother than it does under Windows. The experience has been so good that I'm considering switching my main pc (with a 9070XT) to Linux as well.
No doubt Timur contributed heavily to this given Valves Steamdeck (which uses a very similar but slower GPU).
Given the current hardware prices it's pretty awesome to see someone squeezing maximum performance out of old hardware!
I'm sure Valve probably still deserves the credit, since the Steam Deck uses a RDNA 2 gpu, but the article mentions that Timur specifically worked on gcn1.0 GPUs - e.g. radeon HD 7800/7900 from 2012 (!)
Those are pretty old but Im sure there are reasons. Valve has access to specs from their consumers through steam so maybe a large segment of the third world uses old GPUs for gaming.
My experience has been that for Linux you are always better buying older mid tier hardware because all of the issues and optimisations have already been worked out and those changes have flowed through to your distro so you aren’t waiting on kernel updates.
> those changes have flowed through to your distro so you aren’t waiting on kernel updates
Unless you insist on running a server distro that's consistently obsolete by design (and if the notion of GPU comes into picture, that definitely shouldn't be the case), it shouldn't matter in practice. Every reputable desktop distro has a kernel/mesa stack that's up to date.
5 replies →
I've switched my gaming PC last year to Linux and it's been flawless.
Originally ran a 3070 which matches your "older mid tier" description and then upgraded to a 9070XT maybe 6 months after launch so not so old or mid-tier.
This used to be the case, but new AMD cards were fine about 2 weeks after they released, provided you’re not on an old kernel of course.
I can attest to this myself, my 9070 was a bit rough on launch but worked perfectly soon after.
9 replies →
I switched to Bazzite about 3 weeks ago and am amazed at how well everything "just works". Steam and Battlenet games all running. Nvidia 5070, AMD Rizen 7800x3d, recent gigabyte motherboard.
Steam Deck amazes me, I've had it for years and it doesn't feel dated in the slightest.
It came out in 2022 and it's merely 2026 now. It's a fresh device, it has no reason to feel dated yet.
I'm running my 9070XT on NixOS and it's working great. I have Steam + Blizzard games running.
My gaming PC has a 9070 non-XT, runs Linux, and runs all but a small handful of games [0] just fine. I suspect you'll be happy with the switch.
I run games both new and old and one of my favorite guilty pleasures is looking at the Steam forum for a four, eight, or ten year old game that I've started playing because it has recently become popular again and reading the complaints from Windows users about how a driver update screwed up the game... whether because of glitchy or incorrect graphics or unavoidable crashes. Meanwhile, I'm cruising along on Proton with zero issues. :smug-face:
[0] ...that small handful includes those that go out of their way to be incompatible with Proton...
The 9070 (XT) is great on Linux if you're happy to give up RT. It works but there is a significant perf gap vs Windows.
1 reply →
if you don't play esports game then you don't need to stick in windows anymore
I have AI fatigue, but the potentially for fixing bugs in old hardware is very exciting to me.
Perhaps we will even be able to reverse firmware blobs into open source alternatives?
Yeah AI is extremely good at reverse engineering compared to humans. It's one of those things were there's a huge amount of tedious but not super complex work. I think if you can set up a good harness for the agent it can probably write complete drivers.
The most difficult part is likely that a lot of hardware is easily brickable if you do the wrong thing, so I'm not going to let it loose on e.g. my solar inverter.. even though their software is shit and I'd love to replace it. (Don't buy QCells.)
Direct link to the talk, with timestamp: https://youtu.be/j5W5ErEMnvM?t=21385
I got a r9 285 in 2020 something while the crypto frenzy was still eating up all the gpus. It was 6 years old, got it for like 60 bucks if I remember correctly, best purchase ever, I got to play gta V at 60fps again.
Try to remember back to 2015 the graphics were not that bad. 4k performance was poor but for 1080p 60fps on pretty much anything.
4K is kind of pointless for gaming anyway, IMO. I've got a 32" 4K 165 Hz OLED screen and I much prefer 1080p at 165 Hz over 4K at <= 60 Hz and a pegged GPU. I don't really see pixels either way. 4K is nice for text, though!
Yeah, IMO more people should do 1440p or 1080p, it's _way_ easier to drive and cheaper and it looks great for gaming.
Some other benefits of older GPUs:
Use as a dedicated GPU for encoding and decoding video. Post processing like frame interpolation or superresolution. Use for GPGPU workloads. Run additional monitors independently. Use for GPU passthrough to virtual machines. Use as a backup GPU for troubleshooting. Use for test code without breaking the main GPU
For video decode if it supports the codec you want you're set, but video encode has definitely improved on more modern GPUs. Older GPUs work but you'll likely get worse quality for a given bitrate.
Yeah, if you want good enough video encoding, there's no better option than Intel Arc graphics, maybe a box somewhere just churning B-frames
I'm so happy I didn't throw away my old laptops...
If only AMD did this.
Well, AMD open sources all its stack, making this possible.
AMD supports Mesa precisely so that enthusiasts can do this.
Nvidia doesn't, and their Vulkan stack underperforms on Linux quite significantly.
Except VFX and Hollywood have no qualms using proprietary drivers.
9 replies →
Is there financial incentive for them to bother?
One thing they should've learned from Nvidia is that it's really worth it for them to invest making their devices function as broadly as possible. Crypto and AI waves both benefited Nvidia much more than AMD partly due to their devices being more universally usable.
That "partly" was worth hundreds of billions of dollars but AMD were cheap/shortsighted enough to hire a few dedicated engineers.
3 replies →
Perhaps not but one of the great things about Nvidia is their latest drivers often support very old cards.
7 replies →
Such legendary behaviour
I now have a 2011 or 2012+ 27" iMac everywhere I need a computer, running Linux Mint Mate, and it works better and with less frustration that any new $2500+ Lenovo workstation laptop my employers give me.
Honestly, the folks writing inference drivers for Llama.cpp / GGML would sort of benefit from better compiler work like this.
In general, Valve's work has been exceptional and supplementing AMD's own ROCM/OpenCL and Vulkan team, they've gotten a lot of defaults right and people should work together with Valve to improve support for their chips.
I wonder if some of these could carry over for LLM inference. It will be nice to turn more ewaste GPUs into capable processing units for LLM.
I have a Radeon RX 6900 XT (16 GB VRAM, originally released in 2021), and it's possible to run some lightweight models to have okayish performance and quality of output, but nothing I've tried has come anywhere close to the quality even of the models I can use for free from OpenCode Zen or the free tier of Openrouter. If you want to keep everything local on the same card I have, it requires putting up with a model that's noticeably worse in virtually every metric than what you can get for free elsewhere, and the GPUs this article are talking about are three times as old as mine.
It would be awesome if someone manages to figure out how to get small enough models to fit on older cards to be viable, but I'm not optimistic that it will come without some sort of fundamental architectural innovation rather than incremental improvements, and it's not clear if and when that will happen.
This kinda highlights the level of debt the AI companies are in, and will continue to be in, offering anything for free.
How long is this runway?
1 reply →
Define "small".
The other day I managed to get a context of 195k for Qwen3.5-9b Q4_K_M using a llama.cpp fork that supports TurboQuant:
https://github.com/TheTom/llama-cpp-turboquant
I think you could replicate this with a larger model on your device.
Overall with the right quantisations for both the model and KV cache you can get a lot of mileage out of this old hardware. Speed remains the main limitation, as IIRC I was getting ~26-30tps on a 7700S.
2 replies →
With an extra 8gb of vram you could run qwen 3.8 27b pretty comfortably, which isn't quite as good as frontier models but definitely on par with free models on openrouter and whatnot.
Also you can use multiple GPUs at once, two of your GPUs could run qwen 27b very comfortably, and with great performance.
1 reply →
I have a 6900 XT as well. Unfortunately it is only 512 GB/s.
With AMD the best you can do in the consumer market right now is an RX 7900 XTX which is about 960 GB/s.
Most of these older cards are lacking the physical hardware for fp8 or other lower precisions that most quantized models use. Or the memory to run models at higher precision.
Memory is the bottleneck along with the lack of FP4/FP8 capability at the hardware level.
Awesome.
Is Valve funding this work in particular? How can people donate?
Assuming Valve funds this work, just buy their products. If possible, avoiding credit cards as the CC companies are trying to dictate policies about which games are acceptable and which aren't. I buy the occasional steam card with cash. I encourage everyone to shift a bit of their spending away from CC's in order to reduce the power of these companies to tell us how to live our own lives.
How do you use cash? Do you mean debit or some other digital 'cash'?
1 reply →
Sorry, yes, I meant how could I donate to Timur if he's not being funded my Valve for this.
+1 to buying Valve's products.
[flagged]
[flagged]
[dead]
I understand the good will of the intent but... you have to understand that those driver code paths went thru massive QA over the years. On such complexe hardware, any modifications, even believed benign, can be disastrous for some/many software actually still 'in production'.
This is very risky: one guy QA over a massive amount of software with hardly a few remaining users able to report issues of with those GPUs...
Better have a slow working well tested driver, rather than a broken driver which is supposed to be faster...
That is a valid concern in theory, but in practice, improvements to drivers for old GPUs rarely break things. There are regression tests... and part of it might be Timor being very diligent in his work.
Will Linus torvalds piss this Dev off with childish behaviour, causing the dev to leave kernel dev? Only time will tell