AI Radar
Support
LiveUpdated 2026-09-19 18:08 UTC

Alright, here is the first speed result for @PrismML Ternary Bonsai 2 27B on my rtx 3090

Alright, here is the first speed result for @PrismML Ternary Bonsai 2 27B on my rtx 3090 Quant:…

This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.

Alright, here is the first speed result for @PrismML Ternary Bonsai 2 27B on my rtx 3090 Quant: Ternary-Bonsai-2-27B-PQ2_0.gguf llama.cpp flags: kv f16, fa on max context around 230k at 23.3GB vram utilization Running without mtp or dflash 16k context - tg 54 t/s - prefill 1084 t/s 32k context - tg 48 t/s - prefill 988 t/s 64k context - tg 43 t/s - prefill 809 t/s 128k context - tg 35 t/s - prefill 602 t/s

Posted by AJ (7.5k followers) 1 days ago · 114 likes · 7.8k views · view the original post on X. Kept by the AI Radar as Open & local models.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.