Can a NVIDIA RTX 5090 (32GB) run Gemma 4 26B-A4B (MoE)?

Yes — Gemma 4 26B-A4B (MoE) runs at Q6_K (23.2 GB) at about 175–262 tok/s on a NVIDIA RTX 5090 (32GB).

How much memory does Gemma 4 26B-A4B (MoE) need?

Gemma 4 26B-A4B (MoE) needs about 11.6 GB at 4K context at its smallest quantization. A NVIDIA RTX 5090 (32GB) has 32.0 GB.

Yes — Gemma 4 26B-A4B (MoE) runs on a NVIDIA RTX 5090 (32GB) at Q6_K

Yes — it runs great.

Runs great

Best fit: Gemma 4 26B-A4B (MoE) at Q6_K · 23.2 GB weights · 175–262 tok/s on a NVIDIA RTX 5090 (32GB).

Arena Text Overall · style-controlled

1,438Q6_K untested

gemma-4-26b-a4b · published configuration reference · Q6_K not tested

Arena Text Overall (style-controlled), exact published entry gemma-4-26b-a4b, 2026-10-08: reference rating 1,437.6. Published confidence bounds 1,430.2–1,445.1. 6,092 votes. Published gemma-4-26b-a4b configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected Q6_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: 24.3 GB; Weights + KV cache + runtime overhead
Estimated generation: 175–262 tok/s
Estimated first token: ~0.5s

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.

Gemma 4 26B-A4B (MoE) quantizations on NVIDIA RTX 5090 (32GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	10.6 GB	11.6 GB	238–356 tok/s	Runs great
Q3_K_M	12.7 GB	13.8 GB	224–336 tok/s	Runs great
Q4_K_M	17.0 GB	18.0 GB	201–301 tok/s	Runs great
Q5_K_M	21.2 GB	22.2 GB	183–274 tok/s	Runs great
Q6_K	23.2 GB	24.3 GB	175–262 tok/s	Runs great
Q8_0	26.9 GB	28.0 GB	162–243 tok/s	Tight / slow
FP16	50.5 GB	51.6 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) runs Gemma 4 26B-A4B (MoE) on other machines What to buy to run it →

Ran Gemma 4 26B-A4B (MoE) on a NVIDIA RTX 5090 (32GB)? Add your real numbers →