Can a NVIDIA RTX 5080 (16GB) run Granite 4.2 30B?

Yes — Granite 4.2 30B runs at Q2_K (10.9 GB) at about 51–77 tok/s on a NVIDIA RTX 5080 (16GB).

How much memory does Granite 4.2 30B need?

Granite 4.2 30B needs about 12.7 GB at 4K context at its smallest quantization. A NVIDIA RTX 5080 (16GB) has 16.0 GB.

Yes — Granite 4.2 30B runs on a NVIDIA RTX 5080 (16GB) at Q2_K

Yes — it runs great.

Runs great

Best fit: Granite 4.2 30B at Q2_K · 10.9 GB weights · 51–77 tok/s on a NVIDIA RTX 5080 (16GB).

Arena Text Overall · style-controlled

1,340Q2_K untested

granite-4.2-30b · published configuration reference · Q2_K not tested

Arena Text Overall (style-controlled), exact published entry granite-4.2-30b, 2026-10-08: reference rating 1,339.7. Published confidence bounds 1,329.2–1,350.1. 3,410 votes. Published granite-4.2-30b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q2_K has not been measured by this Arena entry. No quantization quality adjustment is applied.

Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh

Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986

Total memory at 4K context: 12.7 GB; Weights + KV cache + runtime overhead
Estimated generation: 51–77 tok/s
Estimated first token: ~6.4s

Every quantization on this machine

On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.

Granite 4.2 30B quantizations on NVIDIA RTX 5080 (16GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	10.9 GB	12.7 GB	51–77 tok/s	Runs great
Q3_K_M	14.1 GB	16.0 GB	— not resident	Won't fit
Q4_K_M	17.7 GB	19.6 GB	— not resident	Won't fit
Q5_K_M	20.8 GB	22.7 GB	— not resident	Won't fit
Q6_K	24.0 GB	25.9 GB	— not resident	Won't fit
Q8_0	31.1 GB	33.0 GB	— not resident	Won't fit
FP16	58.6 GB	60.4 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA RTX 5080 (16GB) runs Granite 4.2 30B on other machines What to buy to run it →

Ran Granite 4.2 30B on a NVIDIA RTX 5080 (16GB)? Add your real numbers →