Coding with AI / Radeon AI PRO R9700
Radeon AI PRO R9700
Memory: 32 GB.
Memory bandwidth: 640 GB/s.
Generation speed is bound by the chip's bandwidth; memory decides which models fit.
smart and fastQwen3.6-35B-A3B51.5%* on Terminal-Bench 2~127 tok/s · estimated How to run
Qwen3.6-35B-A3B smart
-
Score: 51.5% (Terminal-Bench 2),
source
-
Speed: 127 tok/s (estimate: community-measured predecessor Qwen3.5-35B-A3B Q4_K_XL 127.4 tg (Vulkan, github.com/ggml-org/llama.cpp/discussions/19890): та же архитектура/размер A3B MoE)
- Conditions: engine llama.cpp, quant Q4_K_M, context 128
- Min memory: 24 GB
- Command:
llama-server -m qwen3.6-35b-a3b-Q4_K_M.gguf
Every number above is either a measurement with a source or a labeled estimate with a method.
Unlabeled estimates do not exist on this site.
Ceiling timeline
The strongest model fitting Radeon AI PRO R9700 (32 GB) at its release date, by SWE-bench Verified.
- 2025-08-05 gpt-oss-20b 60.7%
- 2025-08-05 gpt-oss-120b 62.4%
- 2025-12-09 Devstral Small 2 68%
- 2026-04-01 Qwen3.6-35B-A3B 73.4%