# AMD Radeon AI Pro R9700

45 Hacker News commenters recommended AMD Radeon AI Pro R9700 and 9 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** 32 GB of VRAM for much less than Nvidia cards, fast enough for local LLMs, with quiet, easy drivers. The most common caveat is weak vLLM support.

## Why people recommend it

- Lots of VRAM for the price (7 comments): "Radeon R9700 with 32 GB VRAM is relatively affordable for the amount of RAM and with llama.cpp it runs fast enough for most things." ([source](https://news.ycombinator.com/item?id=47200856)) "I have this setup, with 2x 32Gb cards. It's perfect for my needs, and cheaper than anything comparable from NV." ([source](https://news.ycombinator.com/item?id=47745906)) "I have a 32GB R9700, which is much cheaper than a 5090, and runs 27B dense models at ~20 t/s" ([source](https://news.ycombinator.com/item?id=47865654))
- Fast local LLM inference (8 comments): "Radeon R9700 with 32 GB VRAM is relatively affordable for the amount of RAM and with llama.cpp it runs fast enough for most things." ([source](https://news.ycombinator.com/item?id=47200856)) "even a single R9700 runs the main models I am interested in at speeds that are acceptably faster than what I have here" ([source](https://news.ycombinator.com/item?id=49518354)) "For that kind of money I can run 2x AMD R9700 (on a server I already had) and get 150-250 tokens/sec" ([source](https://news.ycombinator.com/item?id=50080248))
- Quiet, low-power, easy drivers (3 comments): "they have been a pleasure to use. Drivers work out-of-the-box, and they are completely quiet when unused." ([source](https://news.ycombinator.com/item?id=47202589)) "I run dual R9700 boxes those idle at 150W Because of a Ryzen AM5" ([source](https://news.ycombinator.com/item?id=49834451)) "R9700s do really well at low wattage and underclocking as well" ([source](https://news.ycombinator.com/item?id=48550218))
- AMD software support keeps improving (2 comments): "have actually gotten more capable through community efforts at optimization, since their launch" ([source](https://news.ycombinator.com/item?id=50243810)) "at least in ComfyUI and local LLMs I'm finding support for AMD has gotten really good." ([source](https://news.ycombinator.com/item?id=49887524))

## What people warn about

- Weak vLLM support (3 comments): "over a year after the release of "pro AI" cards like the r9700, they had basic kernels lacking in vllm" ([source](https://news.ycombinator.com/item?id=49380921)) "Stock vLLM runs so slowly on these cards compared with vLLM forks like Radiance" ([source](https://news.ycombinator.com/item?id=49596592)) "I would advise against if you want to run things like vllm." ([source](https://news.ycombinator.com/item?id=47750516))

## Alternatives hackers recommend

- [NVIDIA GeForce RTX 3090](https://hackerapproved.com/p/nvidia-geforce-rtx-3090.md): 116 recommend
- [NVIDIA GeForce RTX 5090](https://hackerapproved.com/p/nvidia-geforce-rtx-5090.md): 102 recommend
- [NVIDIA RTX PRO 6000](https://hackerapproved.com/p/nvidia-rtx-pro-6000.md): 77 recommend
- [Nvidia GPUs](https://hackerapproved.com/p/nvidia-gpus.md): 67 recommend
- [AMD Radeon GPU](https://hackerapproved.com/p/amd-gpus.md): 48 recommend

## Where to get it

- [See price on Amazon](https://www.amazon.com/s?k=AMD+Radeon+AI+PRO+R9700+GPU&tag=hackerapprove-20) (affiliate link)
- [Official site](https://www.amd.com/en.html)

## Cite as

Hacker Approved, "AMD Radeon AI Pro R9700", https://hackerapproved.com/p/amd-radeon-ai-pro-r9700/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).