PrismML
PrismML
/Bonsai 27B

Quantizations

QuantQuantized bySizeDecodePrefillScoreActions
PrismML
PrismML
3.5 GB41.5 tok/s205.6 tok/sRuns ok

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.

Decode / Prefill Speeds

1 device