RigBaseBuildsGPUsCan it run?GuidesBest rig for…By budgetRent before you buySubmit a buildNewsletterAdvertise

Radeon AI Pro R9700: Qwen3.6 27B on Vulkan, HIP and Ollama, with and without MTP

GPU(s)AMD Radeon AI Pro R9700 (1 of 2 cards in the rig used)
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)32
CPU
Motherboard
RAM
PSU
OtherSecond R9700 not used (no tensor splitting)
Reported total cost
Power

Measured speed (generation tokens/sec)

📏 How measured: reported by the original source; RigBase re-checked the numbers at that source

ModelQuantEnginetok/sDetails
Qwen3.6 27BQ4_K_M + MTP draft head (draft-n-max 3), 64K contextllama.cpp Vulkan66.0⚡ spec-decode (MTP)
Qwen3.6 27BQ4_K_M, no MTPllama.cpp Vulkan31.9
Qwen3.6 27BQ4_K_Mllama.cpp HIP (ROCm)27.1
Qwen3.6 27BQ4_K_MOllama (HIP)26.7

Local AI Frontier, measured 2026-06-30 on one coding prompt (merge sort), 256-512 generated tokens, temperature 0, best of 3 runs per backend. Treat backend ordering as the takeaway rather than exact speeds.

Current GPU street price (estimate, not the builder's cost)Estimated GPU cost for this build today: ≈€1,718
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.

Source: https://localaifrontier.com/benchmarks/qwen3-6-27b-mtp-backend-showdown-r9700/

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 Radeon AI Pro R9700 run Qwen3.6 27B?