More
Submit build

Builds / AMD Radeon AI PRO R9700 32 GB

Radeon AI PRO R9700 32 GB on Windows 11 (llama.cpp Vulkan b12170, Adrenalin 26.9.2): Llama 2 7B Q4_0 at 131.2 tok/s, pp512 4,484

Last updated:

Source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: Llama 2 7B → Muse Glimmer 30B. The hardware numbers are still a useful reference.
GPU(s)
AMD Radeon AI PRO R9700 32 GB
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
32
CPU
Intel Core Ultra 7 265KF
Amazon · eBay (used) · Newegg
Motherboard
ASUS PRIME Z890-P WIFI
Amazon · eBay (used) · Newegg
RAM
64 GB DDR5-6000
Amazon · eBay (used) · Newegg
PSU
not stated
Other
Windows 11 Pro build 26200; AMD Adrenalin 26.9.2 (LLPC); official llama.cpp b12170 (c4fb579) Vulkan release; second GPU in the system is an RTX 5080, R9700 selected with -sm none -mg 1; llama-bench -ngl 100 -fa 0,1, repeated once (within 0.6%)
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Llama 2 7B legacyQ4_0llama.cpp b12170 Vulkan (Windows, AMD proprietary driver)131.164,484 @ 512-token prompt
est. TTFT @8k ≈ 1.8 s (calculated from measured prefill)
context: llama-bench tg128📏 FA on: tg128 131.16 ± 0.11; FA off: 126.74, pp512 4,123.70

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Owner's run in llama.cpp's long-running Vulkan scoreboard discussion (6 Nov 2026), described as the first Windows gfx1201 result there. Linux entries in the same thread show 152.70 tok/s / 5,907.66 pp512 for the R9700, so Windows with AMD's driver came in about 14% slower at generation on this standard test. Different systems and builds, so treat the gap as indicative.

Current GPU street price (estimate, not the builder's cost)Estimated GPU cost for this build today: ≈€1,848
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.
Source: https://github.com/ggml-org/llama.cpp/discussions/10879

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/radeon-ai-pro-r9700-32gb-windows-11-vulkan-llama2-7b-adrenalin.svg)](https://getrigbase.com/builds/radeon-ai-pro-r9700-32gb-windows-11-vulkan-llama2-7b-adrenalin/)

HTML

<a href="https://getrigbase.com/builds/radeon-ai-pro-r9700-32gb-windows-11-vulkan-llama2-7b-adrenalin/" rel="noopener"><img src="https://getrigbase.com/badge/radeon-ai-pro-r9700-32gb-windows-11-vulkan-llama2-7b-adrenalin.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase · How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)