Fastest
unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q5_K_XL
26B
69.8 tok/s
Highest token generation speed at 69.8 tok/s.
Hardware Benchmarks
Best Local LLM Performance for Ai Pro R9700
Compare Ai Pro R9700 benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 32GB
Recommended Models
Models we recommend for Ai Pro R9700.
Best quality & Largest context
unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL
30B
34.5 tok/sQuality 85.8Context 131,072 tokens
Highest completed quality score at 85.8. Largest context that fits in 32GB VRAM, at 131,072 tokens.
Frequently asked questions
Which models actually run best on the Ai Pro R9700, by task, from community benchmark data.
- What is the best local model for coding on the Ai Pro R9700?
- On the Ai Pro R9700, unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL ranks first for coding in our benchmarks (77.9/100 at ~34.5 tok/s).
- What is the best local model for agentic workflows on the Ai Pro R9700?
- On the Ai Pro R9700, unsloth/Muse-Glimmer-30B-GGUF:UD-Q4_K_XL ranks first for agentic workflows in our benchmarks (89.1/100 at ~34.5 tok/s). unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q5_K_XL is faster (~69.7 tok/s) and still scores well (81.8/100) β a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon AI PRO R9700.