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

Compatibility check

Can I run Llama 3.2 1B Instruct on NVIDIA DGX Spark (GB10)?

Yes — it runs.best quant:

Decode speed

300 tok/sest

Usable context

33K

Memory

128 GB

Fits in memory300 tok/sest · 33K ctx

Fits in memory256 tok/sest · 33K ctx

Fits in memory171 tok/sest · 33K ctx

What is quantisation? →

Llama 3.2 1B Instruct

1.2B · full specs & benchmarks →

NVIDIA DGX Spark (GB10)

128 GB · everything it runs →