LLMap
Models /Granite 4.1 8B /Can I run it?
Compatibility check

Can I run Granite 4.1 8B on GeForce RTX 5090?

Yes — it runs.best quant:
Decode speed
269 tok/sest
Usable context
131K
Memory
32 GB
Fits in memory269 tok/sest · 131K ctx
Fits in memory229 tok/sest · 131K ctx
Fits in memory153 tok/sest · 66K ctx
What is quantisation? →
Granite 4.1 8B
8.8B · full specs & benchmarks →
GeForce RTX 5090
32 GB · everything it runs →