More
Submit build

Builds / AMD Radeon 890M iGPU (Ryzen AI 9 HX 370, RDNA 3.5, shared me

Radeon 890M iGPU (Ryzen AI 9 HX 370): Qwen3.5 35B-A3B Q4_K_M at 24.8 tok/s on llama.cpp Vulkan b10830, 20.3 on b12387 (tg regression report)

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: Qwen3.5 35B-A3B → Qwen3.6 35B-A3B, Qwen3.5 35B-A3B → Qwen3.6 35B-A3B. The hardware numbers are still a useful reference.
GPU(s)
AMD Radeon 890M iGPU (Ryzen AI 9 HX 370, RDNA 3.5, shared memory)
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
48
CPU
AMD Ryzen AI 9 HX 370 (12C/24T Zen 5)
Amazon · eBay (used) · Newegg
Motherboard
not stated
Amazon · eBay (used) · Newegg
RAM
62 GiB system RAM (GTT raised to 48 GiB, 512 MiB BIOS carve-out)
Amazon · eBay (used) · Newegg
PSU
not stated
Other
Arch Linux, kernel 7.2.11, Mesa 26.2.2 RADV, GCC 16.2.1; llama-bench, identical build configs; vram_gb here is the GTT limit the GPU may use
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.5 35B-A3B legacyUnsloth UD-Q4_K_Mllama.cpp b10830 465e49b9c (Vulkan, RADV)24.8251 @ 512-token prompt
est. TTFT @8k ≈ 32.6 s (calculated from measured prefill)
context: llama-bench tg128📏 llama-bench -ngl 99: tg128 24.80 ± 0.04 (ngl 40 22.98, ngl 20 17.66, ngl 0 14.27)
Qwen3.5 35B-A3B legacyUnsloth UD-Q4_K_Mllama.cpp b12387 a956a852c (Vulkan, RADV)20.32293 @ 512-token prompt
est. TTFT @8k ≈ 28.0 s (calculated from measured prefill)
context: llama-bench tg128📏 Same machine and command on the newer build: tg128 20.32 ± 0.06 (-18.1%), pp512 up 16.6%; Arch llama-cpp 0.9.0 package (b12110, asserts on) 21.45

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.

Reporter's own measurements in an open llama.cpp bug report (14 Nov 2026): raw token generation on the 890M iGPU dropped ~18% between September (b10830) and November (b12387) builds while prompt processing got faster. If you run a Radeon 780M/890M-class iGPU, the older build is faster for chat-length generation until this is resolved.

Source: https://github.com/ggml-org/llama.cpp/issues/32290

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-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387.svg)](https://getrigbase.com/builds/radeon-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387/)

HTML

<a href="https://getrigbase.com/builds/radeon-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387/" rel="noopener"><img src="https://getrigbase.com/badge/radeon-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387.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)