Models /Llama 3.1 8B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.1 8B Instruct on H200 141GB SXM?

Yes — it runs.best quant:

Decode speed

792 tok/sest

Usable context

131K

Memory

141 GB

Fits in memory792 tok/sest · 131K ctx

Fits in memory675 tok/sest · 131K ctx

Fits in memory452 tok/sest · 131K ctx

What is quantisation? →

Llama 3.1 8B Instruct

8B · full specs & benchmarks →

141 GB · everything it runs →