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

Can I run Llama 3.2 3B Instruct on L40S?

Yes — it runs.best quant:
Decode speed
356 tok/sest
Usable context
131K
Memory
48 GB
Fits in memory356 tok/sest · 131K ctx
Fits in memory304 tok/sest · 131K ctx
Fits in memory203 tok/sest · 131K ctx
What is quantisation? →
Llama 3.2 3B Instruct
3.2B · full specs & benchmarks →
L40S
48 GB · everything it runs →