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

Compatibility check

Can I run Llama 3.3 70B Instruct on NVIDIA DGX Spark (GB10)?

Yes — it runs.best quant: Q4_K_M

Decode speed

5 tok/sest

Usable context

131K

Memory

128 GB

Q4_K_MFits in memory5 tok/sest · 131K ctx

Q5_K_MFits in memory4 tok/sest · 131K ctx

Q8_0Fits in memory3 tok/sest · 131K ctx

Llama 3.3 70B Instruct

70.6B · full specs & benchmarks →

NVIDIA DGX Spark (GB10)

128 GB · everything it runs →