Builds / AMD Ryzen AI Max+ PRO 495 (Radeon 8065S iGPU, 40 CUs)
Minisforum MS-S1 MAX (Ryzen AI Max+ PRO 495, 192 GB): gpt-oss 120B at 55.8 tok/s
Source: hommie.net ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- AMD Ryzen AI Max+ PRO 495 (Radeon 8065S iGPU, 40 CUs)
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 192
- CPU
- AMD Ryzen AI Max+ PRO 495 ("Gorgon Halo")
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 192 GB LPDDR5X-8533 unified (GPU limit raised to 170 GB via ttm.pages_limit)
- PSU
- not stated
- Other
- 2 TB SSD, dual 10GbE, Ubuntu Server 26.04.1 (kernel 7.0), llama.cpp Vulkan, flash attention on, q8_0 KV cache, ubatch 2048
- Reported total cost
- $7,399 (≈€6,602)
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| gpt-oss 120B | MXFP4 | llama.cpp Vulkan | 55.8 | |
| gpt-oss 120B | MXFP4, 32K context | llama.cpp Vulkan | 45.1 | |
| Qwen3.8 27B | Q8 (author: "about 8 tok/s") | llama.cpp Vulkan | 8 | |
| MiniMax M2.7 legacy | IQ4_XS | llama.cpp Vulkan | 29.5 | |
| MiniMax M2.7 legacy | IQ4_XS, 32K context | llama.cpp Vulkan | 17.3 | |
| DeepSeek V4 Flash legacy | IQ3_S | llama.cpp Vulkan | 17.4 | |
| DeepSeek V4 Flash legacy | IQ3_S, 32K context | llama.cpp Vulkan | 12.2 |
Jake's Garage, 2026. Cost is the author's pre-order price. One of the first owner-measured Ryzen AI Max+ 495 results. The author found the default f16 KV cache was the long-context bottleneck on Vulkan; q8_0 KV roughly doubled 32K prompt processing. ROCm was slower than tuned Vulkan for generation.
Source: https://www.hommie.net/posts/ai-box.html
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
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)