More
Submit build

Builds / AMD Radeon AI Pro R9700 (1 of 2 cards in the rig used)

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

Source: localaifrontier.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: Qwen3.6 27B → Qwen3.8 27B, Qwen3.6 27B → Qwen3.8 27B, Qwen3.6 27B → Qwen3.8 27B, Qwen3.6 27B → Qwen3.8 27B. The hardware numbers are still a useful reference.
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
not stated
Motherboard
not stated
RAM
not stated
PSU
not stated
Other
Second R9700 not used (no tensor splitting)
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sDetails
Qwen3.6 27B legacyQ4_K_M + MTP draft head (draft-n-max 3), 64K contextllama.cpp Vulkan66.0⚡ spec-decode (MTP)
Qwen3.6 27B legacyQ4_K_M, no MTPllama.cpp Vulkan31.9
Qwen3.6 27B legacyQ4_K_Mllama.cpp HIP (ROCm)27.1
Qwen3.6 27B legacyQ4_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: ≈€1,848
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?