More
Submit build

Can 2x Radeon AI Pro R9700 run Qwen3.6 27B?

Last updated:

Yes. Measured 62.75 tok/s generation (vLLM tuned build (vllm-radiance), TP=2 + MTP, FP8; source).

Every measured result for Qwen3.6 27B on 2x Radeon AI Pro R9700

BuildQuant / setupEnginetok/s
2x Radeon AI PRO R9700 32 GB (Threadripper PRO 5995WX): Qwen3.6 27B at 23.4 tok/s on llama.cpp Q4_K_M, 15.9 on stock vLLM FP8 TP=2, 62.75 with tuned vLLM + MTP (Puget Systems)FP8vLLM tuned build (vllm-radiance), TP=2 + MTP62.75source
2x Radeon AI PRO R9700 32 GB, vLLM with custom RDNA4 FP8 kernels: Qwen3.6 27B FP8 at 26.5 tok/s single stream, 55.3 with MTP (k=3)FP8 (Qwen/Qwen3.6-27B-FP8)vLLM fork esdmax-r9700-fp8, ROCm 7.2, TP=2 + MTP k=355.3source
2x Radeon AI PRO R9700 32 GB (Threadripper PRO 5995WX): Qwen3.6 27B at 23.4 tok/s on llama.cpp Q4_K_M, 15.9 on stock vLLM FP8 TP=2, 62.75 with tuned vLLM + MTP (Puget Systems)FP8vLLM tuned build (vllm-radiance), TP=232.0source
2x Radeon AI PRO R9700 32 GB, vLLM with custom RDNA4 FP8 kernels: Qwen3.6 27B FP8 at 26.5 tok/s single stream, 55.3 with MTP (k=3)FP8 (Qwen/Qwen3.6-27B-FP8)vLLM fork esdmax-r9700-fp8, ROCm 7.2, TP=226.5source
2x Radeon AI PRO R9700 32 GB (Threadripper PRO 5995WX): Qwen3.6 27B at 23.4 tok/s on llama.cpp Q4_K_M, 15.9 on stock vLLM FP8 TP=2, 62.75 with tuned vLLM + MTP (Puget Systems)Q4_K_M (GGUF)llama.cpp ROCm, layer split across both cards23.4source
2x Radeon AI PRO R9700 32 GB (Threadripper PRO 5995WX): Qwen3.6 27B at 23.4 tok/s on llama.cpp Q4_K_M, 15.9 on stock vLLM FP8 TP=2, 62.75 with tuned vLLM + MTP (Puget Systems)FP8vLLM v0.20.2 ROCm (stock image), TP=215.88source

Memory: 2x Radeon AI Pro R9700 has 64 GB. Qwen3.6 27B weights are about 16.7 GB at Q4_K_M (27.32B 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 Qwen3.6 27B: best home rig for Qwen3.6 27B.

Qwen3.6 27B on other hardware: DGX Spark (GB10) · RTX 3090 · RTX 4090 · RTX 5090 · Radeon AI Pro R9700 · Strix Halo (Radeon 8060S)

Not enough VRAM? Rent before you buy. Run Qwen3.6 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.