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

Compatibility check

Can I run Llama 3.1 8B Instruct on B200 (SXM 192GB)?

Yes — it runs.best quant:

Decode speed

1320 tok/sest

Usable context

131K

Memory

192 GB

Fits in memory1320 tok/sest · 131K ctx

Fits in memory1125 tok/sest · 131K ctx

Fits in memory753 tok/sest · 131K ctx

What is quantisation? →

Llama 3.1 8B Instruct

8B · full specs & benchmarks →

B200 (SXM 192GB)

192 GB · everything it runs →