Models /Llama 3.3 70B Instruct /Can I run it?

Compatibility check

Can I run Llama 3.3 70B Instruct on H200 141GB SXM?

Yes — it runs.best quant: Q4_K_M

Decode speed

90 tok/sest

Usable context

131K

Memory

141 GB

Q4_K_MFits in memory90 tok/sest · 131K ctx

Q5_K_MFits in memory77 tok/sest · 131K ctx

Q8_0Fits in memory51 tok/sest · 131K ctx

Llama 3.3 70B Instruct

70.6B · full specs & benchmarks →

141 GB · everything it runs →