Fastest & Best quality & Largest context tested
zai-org/glm-4.6v-flash
Unknown
13.2 tok/sQuality 28.0Context 1,024 tokens
Highest token generation speed at 13.2 tok/s. Highest completed quality score at 28.0. Largest context window tested on this hardware, at 1,024 tokens. Its memory wasn't measured, so this doesn't show the full window fits.