LLMap
Models /Llama 3.2 1B Instruct /Can I run it?
Compatibility check

Can I run Llama 3.2 1B Instruct on H200 141GB SXM?

Yes — it runs.best quant:
Decode speed
5278 tok/sest
Usable context
33K
Memory
141 GB
Fits in memory5278 tok/sest · 33K ctx
Fits in memory4499 tok/sest · 33K ctx
Fits in memory3012 tok/sest · 33K ctx
What is quantisation? →
Llama 3.2 1B Instruct
1.2B · full specs & benchmarks →
H200 141GB SXM
141 GB · everything it runs →