Can a NVIDIA RTX 5070 Ti (16GB) run GPT-OSS 20B (MoE)?

Yes — GPT-OSS 20B (MoE) runs at Q6_K (12.0 GB) at about 166–249 tok/s on a NVIDIA RTX 5070 Ti (16GB).

How much memory does GPT-OSS 20B (MoE) need?

GPT-OSS 20B (MoE) needs about 12.4 GB at 4K context at its smallest quantization. A NVIDIA RTX 5070 Ti (16GB) has 16.0 GB.

Yes — GPT-OSS 20B (MoE) runs on a NVIDIA RTX 5070 Ti (16GB) at Q6_K

Yes — it runs great.

Runs great

Best fit: GPT-OSS 20B (MoE) at Q6_K · 12.0 GB weights · 166–249 tok/s on a NVIDIA RTX 5070 Ti (16GB).

Arena Text Overall · style-controlled

1,317Q6_K untested

gpt-oss-20b · published configuration reference · Q6_K not tested

Arena Text Overall (style-controlled), exact published entry gpt-oss-20b, 2026-10-08: reference rating 1,317.3. Published confidence bounds 1,310.9–1,323.8. 10,418 votes. Published gpt-oss-20b 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: 12.9 GB; Weights + KV cache + runtime overhead
Estimated generation: 166–249 tok/s
Estimated first token: ~1.0s

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.

GPT-OSS 20B (MoE) quantizations on NVIDIA RTX 5070 Ti (16GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	11.5 GB	12.4 GB	170–256 tok/s	Runs great
Q3_K_M	11.5 GB	12.4 GB	170–255 tok/s	Runs great
Q4_K_M	11.6 GB	12.5 GB	169–254 tok/s	Runs great
Q5_K_M	11.7 GB	12.6 GB	169–253 tok/s	Runs great
Q6_K	12.0 GB	12.9 GB	166–249 tok/s	Runs great
Q8_0	12.1 GB	13.0 GB	166–249 tok/s	Tight / slow
FP16	13.8 GB	14.7 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA RTX 5070 Ti (16GB) runs GPT-OSS 20B (MoE) on other machines What to buy to run it →

Ran GPT-OSS 20B (MoE) on a NVIDIA RTX 5070 Ti (16GB)? Add your real numbers →