Can Strix Halo (Radeon 8060S) run Gemma 4 12B?

Q: Can Strix Halo (Radeon 8060S) run Gemma 4 12B?

Yes. Measured 25.9 tok/s generation on Strix Halo (Radeon 8060S), via llama.cpp b11669 (Vulkan), QAT Q4_0 (7.0 GB, Google's file). Source: https://measuredlocally.com/strix-halo.html

Last updated: 3 Nov 2026

Yes. Measured 25.9 tok/s generation (llama.cpp b11669 (Vulkan), QAT Q4_0 (7.0 GB, Google's file); source).

Every measured result for Gemma 4 12B on Strix Halo (Radeon 8060S)

Build	Quant / setup	Engine	tok/s
HP ZBook Ultra G1a (Ryzen AI Max+ 395, 64 GB): gpt-oss 20B at 67.2 tok/s, Qwen3.6 35B-A3B at 52.3 (llama.cpp Vulkan)	QAT Q4_0 (7.0 GB, Google's file)	llama.cpp b11669 (Vulkan)	25.9	source

Memory: Strix Halo (Radeon 8060S) has 64 GB. Gemma 4 12B weights are about 7.3 GB at Q4_K_M (11.91B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Gemma 4 12B: best home rig for Gemma 4 12B.

Gemma 4 12B on other hardware: Apple M4 · RTX 3060 12GB · RTX 4090 · RTX 5070 Ti · RTX 5090 · RTX Spark N1X

Other models measured on Strix Halo (Radeon 8060S): Gemma 4 26B-A4B · Gemma 4 31B · Kolibri-1 · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 120B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Gemma 4 12B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.