can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at FP16 · 17.6 GB · 37–55 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB122–183 tok/sRuns great
Q3_K_M4.4 GB106–158 tok/sRuns great
Q4_K_M5.4 GB92–139 tok/sRuns great
Q5_K_M6.3 GB83–125 tok/sRuns great
Q6_K7.2 GB75–113 tok/sRuns great
Q8_09.4 GB62–93 tok/sRuns great
FP1617.6 GB37–55 tok/sRuns great

Ran Granite 4.2 8B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →