Builds / AMD Ryzen AI Max+ PRO 395 (Radeon 8060S iGPU, 32 GB dedicate
HP ZBook Ultra G1a (Strix Halo laptop, 128 GB): Qwen3.6 35B-A3B at 59.4 tok/s, gpt-oss 120B at 44.7
Source: petronellatech.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
- GPU(s)
- AMD Ryzen AI Max+ PRO 395 (Radeon 8060S iGPU, 32 GB dedicated)
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 128
- CPU
- AMD Ryzen AI Max+ PRO 395
Amazon · eBay (used) · Newegg - Motherboard
- not stated
- RAM
- 128 GB unified
- PSU
- not stated
- Other
- Laptop on Windows 11, HP Optimized power plan, plugged in; llama.cpp b11213 (Vulkan and ROCm 7.13), Ollama 0.34.0
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| Qwen3.6 35B-A3B | Q4_K_M | llama.cpp b11213 Vulkan | 59.4 | |
| gpt-oss 120B | MXFP4 | llama.cpp b11213 Vulkan | 44.7 | |
| Qwen3.6 35B-A3B | 4-bit | Ollama 0.34.0 | 54.4 | |
| Gemma 4 26B-A4B | 4-bit | Ollama 0.34.0 | 51.8 | |
| Gemma 4 31B | 4-bit | Ollama 0.34.0 | 8.8 | |
| Qwen3.6 27B legacy | 4-bit | Ollama 0.34.0 | 11.4 |
Measured 27 Sep 2026 by Petronella Technology Group. llama-bench tg128, empty context, mean of 3. Same-day DGX Spark with the same build: 69.5 (Qwen3.6 35B-A3B) and 59.5 (gpt-oss 120B). gpt-oss 120B at 32K context collapsed to 4.7 tok/s on Vulkan but held 32.3 on ROCm.
Source: https://petronellatech.com/blog/dgx-spark-vs-strix-halo-vs-gorgon-halo-local-llm-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 Gemma 4 26B-A4B? · Can Strix Halo (Radeon 8060S) run Gemma 4 31B? · Can Strix Halo (Radeon 8060S) run Qwen3.6 27B? · Can Strix Halo (Radeon 8060S) run Qwen3.6 35B-A3B? · Can Strix Halo (Radeon 8060S) run gpt-oss 120B?