Comment Comment by canpan Just ran llama-bench at home with the similar priced AMD AI PRO R9700 32G. The phoronix numbers look extremely low? Probably I misunderstand their test bench. Anyway, here are some numbers. Maybe someone with access to a B70 can post a comparison.Tried to use the same model as the article:llama-bench -m gpt-oss-20b-Q8_0.gguf -ngl 999 -p 2048 -n 128AMD R9700 pp2048=3867 tg128=175And a bigger model, because testing a tiny model with a 32GB card feels like a waste:llama-bench -m Qwen3.6-27B-UD-Q6_K_XL.gguf -ngl 999 -p 2048 -n 128AMD R9700 pp2048=917 tg128=22 parent canpan 6 months ago
Tried to use the same model as the article:
llama-bench -m gpt-oss-20b-Q8_0.gguf -ngl 999 -p 2048 -n 128
AMD R9700 pp2048=3867 tg128=175
And a bigger model, because testing a tiny model with a 32GB card feels like a waste:
llama-bench -m Qwen3.6-27B-UD-Q6_K_XL.gguf -ngl 999 -p 2048 -n 128
AMD R9700 pp2048=917 tg128=22