Ask HN: What can I do with a single R9700?

#1

Post by scott01 » Sat, Aug 08, 2026, 2:18 PM UTC

Hi HN,

I’m considering getting an R9700, budget only for one unit currently. Is there anything useful I can do with local LLMs within its 32G VRAM? I’m also thinking to try and learn building a simple inference engine. Any thoughts?

Re: Ask HN: What can I do with a single R9700?

#2

Post by spottedmarley » Sat, Aug 08, 2026, 3:11 PM UTC

For learning it's all you need. Pick a good small model, I would recommend Qwen3.5 there are models ranging from 0.8b params (will run on a smart phone) all the way up to 397b params .. I run the 122b param model daily with 128GB vram and get 20+tk/sec. regardless of the model, you can learn all about how to host and harness a model with any size

Re: Ask HN: What can I do with a single R9700?

#3

Post by scott01 » Sat, Aug 08, 2026, 3:38 PM UTC

spottedmarley wrote: post #2

For learning it's all you need. Pick a good small model, I would recommend Qwen3.5 there are models ranging from 0.8b params (will run on a smart phone) all the way up to 397b params .. I run the 122b param model daily with 128GB vram and get 20+tk/sec. regardless of the model, you can learn all about how to host and harness a model with any size

With this amount of VRAM, do you happen to be using a Strix Halo or a Mac?

Re: Ask HN: What can I do with a single R9700?

#4

Post by rdx-amw » Sat, Aug 08, 2026, 5:19 PM UTC

Plenty - you could do both with an R9700.

Unless it's CUDA only, a fair amount of software now supports AMD ROCm. And if you're already wanting to write an inference engine, 32G will be more than fine.

I've had a R9700 and it'd run the lower quants (4-5 bit?) of Qwen 3.5 27B reasonably attached to Hermes Agent. Not quite a 3090, but still respectable speeds.

Re: Ask HN: What can I do with a single R9700?

#5

Post by moustache_hn » Sat, Aug 08, 2026, 5:35 PM UTC

[flagged]

Re: Ask HN: What can I do with a single R9700?

#6

Post by FloatArtifact » Sat, Aug 08, 2026, 5:36 PM UTC

rdx-amw wrote: post #4

Plenty - you could do both with an R9700. Unless it's CUDA only, a fair amount of software now supports AMD ROCm. And if you're already wanting to write an inference engine, 32G will be more than fine. I've had a R9700 and it'd run the lower quants (4-5 bit?) of Qwen 3.5 27B reasonably attached to Hermes Agent. Not quite a 3090, but still respectable speeds.

You say that as it's in the past, have you moved on to something else?