Can Strix Halo (Radeon 8060S) run Qwen3.8 27B?

Q: Can Strix Halo (Radeon 8060S) run Qwen3.8 27B?

Yes. Measured 18.01 tok/s generation on Strix Halo (Radeon 8060S), via llama.cpp Vulkan (RADV), Q6_K + MTP (draft-n-max 2). Source: https://sleepingrobots.com/dreams/qwen38-mtp-strix-halo/

Yes. Measured 18.01 tok/s generation (llama.cpp Vulkan (RADV), Q6_K + MTP (draft-n-max 2); source).

Every measured result for Qwen3.8 27B on Strix Halo (Radeon 8060S)

Build	Quant / setup	Engine	tok/s
Strix Halo (Ryzen AI Max+ 395, 128 GB): Qwen3.8 27B Q6_K, 9.6 to 18 tok/s with MTP	Q6_K + MTP (draft-n-max 2)	llama.cpp Vulkan (RADV)	18.01	source
Strix Halo (Corsair AI Workstation 300, 128 GB): ROCm vs Vulkan on Qwen3.8 27B and Qwen3.6 35B-A3B	Q8_0 + MTP (draft-n-max 3), coding workload, reasoning on	llama.cpp ROCm	15.67	source
Strix Halo (Ryzen AI Max+ 395, 128 GB): Qwen3.8 27B Q6_K, 9.6 to 18 tok/s with MTP	Q6_K + MTP (draft-n-max 5)	llama.cpp Vulkan (RADV)	15.16	source
Strix Halo (Corsair AI Workstation 300, 128 GB): ROCm vs Vulkan on Qwen3.8 27B and Qwen3.6 35B-A3B	Q8_0 + MTP (draft-n-max 3), coding workload, reasoning on	llama.cpp Vulkan	13.19	source
Strix Halo mini PC (Ryzen AI Max+ 395, 128 GB): Qwen3.8 27B at 12.6 tok/s Q4_K_M, 7.7 Q8_0	Q4_K_M	llama.cpp/Ollama, ROCm	12.6	source
Strix Halo (Ryzen AI Max+ 395, 128 GB): Qwen3.8 27B Q6_K, 9.6 to 18 tok/s with MTP	Q6_K, no MTP	llama.cpp Vulkan (RADV)	9.59	source
Strix Halo (Corsair AI Workstation 300, 128 GB): ROCm vs Vulkan on Qwen3.8 27B and Qwen3.6 35B-A3B	Q8_0, llama-bench tg128	llama.cpp Vulkan	7.77	source
Strix Halo (Corsair AI Workstation 300, 128 GB): ROCm vs Vulkan on Qwen3.8 27B and Qwen3.6 35B-A3B	Q8_0, llama-bench tg128	llama.cpp ROCm	7.76	source
Strix Halo mini PC (Ryzen AI Max+ 395, 128 GB): Qwen3.8 27B at 12.6 tok/s Q4_K_M, 7.7 Q8_0	Q8_0, --reasoning off	llama.cpp/Ollama, ROCm	7.7	source

Memory: Strix Halo (Radeon 8060S) has 128 GB. Qwen3.8 27B weights are about 16.5 GB at Q4_K_M (27B 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 Qwen3.8 27B: best home rig for Qwen3.8 27B.

Qwen3.8 27B on other hardware: 2x Apple M5 Ultra · 2x Intel Arc Pro B70 · 2x RTX 5070 Ti · 2x Tesla V100 32GB · 4x Apple M5 Ultra · Apple M3 Ultra · Apple M5 Ultra · DGX Spark (GB10) · Intel Arc Pro B70 · RTX 3060 12GB · RTX 3090 · RTX 4060 Ti 16GB · RTX 5070 Ti · RTX 5090 · RTX Pro 6000 Max-Q (Blackwell, 96 GB, 300 W) · RTX Spark N1X · Radeon AI Pro R9700

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

Not enough VRAM? Rent before you buy. Run Qwen3.8 27B 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.