Can a NVIDIA RTX 6000 Ada (48GB) run Llama 4 Scout (MoE)?

Just about — Llama 4 Scout (MoE) runs at Q2_K (39.6 GB) at about 79–118 tok/s on a NVIDIA RTX 6000 Ada (48GB).

How much memory does Llama 4 Scout (MoE) need?

Llama 4 Scout (MoE) needs about 41.2 GB at 4K context at its smallest quantization. A NVIDIA RTX 6000 Ada (48GB) has 48.0 GB.

Tight fit: Llama 4 Scout (MoE) on a NVIDIA RTX 6000 Ada (48GB) at Q2_K

Yes, but it's tight.

Tight / slow

Best fit: Llama 4 Scout (MoE) at Q2_K · 39.6 GB weights · 79–118 tok/s on a NVIDIA RTX 6000 Ada (48GB).

Arena Text Overall · style-controlled

1,322Q2_K untested

llama-4-scout-17b-16e-instruct · published configuration reference · Q2_K not tested

Arena Text Overall (style-controlled), exact published entry llama-4-scout-17b-16e-instruct, 2026-10-08: reference rating 1,321.5. Published confidence bounds 1,316.8–1,326.3. 29,836 votes. Published llama-4-scout-17b-16e-instruct 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: 41.2 GB; Weights + KV cache + runtime overhead
Estimated generation: 79–118 tok/s
Estimated first token: ~2.3s

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.

Llama 4 Scout (MoE) quantizations on NVIDIA RTX 6000 Ada (48GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	39.6 GB	41.2 GB	79–118 tok/s	Tight / slow
Q3_K_M	51.8 GB	53.4 GB	— not resident	Won't fit
Q4_K_M	65.4 GB	67.0 GB	— not resident	Won't fit
Q5_K_M	76.6 GB	78.2 GB	— not resident	Won't fit
Q6_K	88.4 GB	90.0 GB	— not resident	Won't fit
Q8_0	114.5 GB	116.1 GB	— not resident	Won't fit
FP16	215.6 GB	217.2 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runs Llama 4 Scout (MoE) on other machines What to buy to run it →

Ran Llama 4 Scout (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →