LLMap
Models /Llama 3.2 3B Instruct /Can I run it?
Compatibility check

Can I run Llama 3.2 3B Instruct on H100 80GB SXM?

Yes — it runs.best quant:
Decode speed
1381 tok/sest
Usable context
131K
Memory
80 GB
Fits in memory1381 tok/sest · 131K ctx
Fits in memory1178 tok/sest · 131K ctx
Fits in memory788 tok/sest · 131K ctx
What is quantisation? →
Llama 3.2 3B Instruct
3.2B · full specs & benchmarks →
H100 80GB SXM
80 GB · everything it runs →