Minisforum MS-S1 MAX (Strix Halo, 128 GB): Qwen3.6 35B-A3B at 62 tok/s on llama.cpp Vulkan
| GPU(s) | AMD Ryzen AI Max+ 395 (Radeon 8060S iGPU) Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 128 |
| CPU | AMD Ryzen AI Max+ 395 Amazon · eBay (used) · Newegg |
| Motherboard | |
| RAM | 128 GB unified |
| PSU | |
| Other | Minisforum MS-S1 MAX mini PC; Ubuntu 26.04, kernel 7.0, Mesa RADV (Vulkan 1.4.335), ROCm 10.1.0, llama.cpp commit d7a695e |
| Reported total cost | $3,799 (≈€3,390) |
| Power |
Measured speed (generation tokens/sec)
📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| Qwen3.6 35B-A3B | Q4_K_M (Unsloth) | llama.cpp Vulkan | 62 | |
| Qwen3.6 35B-A3B | Q8_0 | llama.cpp Vulkan | 54 | |
| Qwen3.6 35B-A3B | Q4_K_M (Unsloth) | llama.cpp ROCm | 51 | |
| Qwen3.6 35B-A3B | Q4_K_M (Unsloth) | llama.cpp Vulkan + MTP | 93 | ⚡ spec-decode (MTP) |
Measured 6 Oct 2026 (thinking-mode workload, medians). MTP figure is from the 7 Oct update (code/JSON output, short check). llama-bench tg128 at depth 0: Vulkan Q4 63, Q8 54, ROCm Q4 54, ROCm Q8 48; at 65K depth Vulkan Q4 43. Cost is what the author says he paid.
Source: https://vitorpontual.com/posts/two-ai-boxes-3-the-benchmarks/
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)
Quick answers: Can Strix Halo (Radeon 8060S) run Qwen3.6 35B-A3B?