LLMap
Models /STT 2.6b en /Can I run it?
Compatibility check

Can I run STT 2.6b en on GeForce RTX 5070?

Yes — it runs.best quant:
Decode speed
341 tok/sest
Usable context
262K
Memory
12 GB
Fits in memory341 tok/sest · 262K ctx
Fits in memory291 tok/sest · 262K ctx
Fits in memory195 tok/sest · 131K ctx
What is quantisation? →
STT 2.6b en
2.6B · full specs & benchmarks →
GeForce RTX 5070
12 GB · everything it runs →