Can Strix Halo (Radeon 8060S) run Qwen3.5 122B?
Last updated:
Yes. Measured 23.6 tok/s generation (llama.cpp b11401 (Windows x64 Vulkan, unmodified), Unsloth UD-IQ4_XS (60.2 GB / 56.1 GiB, 3 shards); source).
Every measured result for Qwen3.5 122B on Strix Halo (Radeon 8060S)
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| GMKtec EVO-X3 (Strix Halo 128 GB, Windows 11, stock llama.cpp Vulkan): Qwen3.6 35B-A3B at 61.8 tok/s, Qwen3.5 122B at 23.6 (idle machine) | Unsloth UD-IQ4_XS (60.2 GB / 56.1 GiB, 3 shards) | llama.cpp b11401 (Windows x64 Vulkan, unmodified) | 23.6 | source |
Memory: Strix Halo (Radeon 8060S) has 128 GB. Qwen3.5 122B weights are about 74.6 GB at Q4_K_M (122B 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 Qwen3.5 122B: best home rig for Qwen3.5 122B.
Qwen3.5 122B on other hardware: RTX Spark N1X
Other models measured on Strix Halo (Radeon 8060S): Gemma 4 12B · Gemma 4 26B-A4B · Gemma 4 31B · Kolibri-1 · LFM2.5 24B-A2B · 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 Qwen3.5 122B 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.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.