gpt-oss-20b hardware requirements

About the model

Parameters: 20.9B total · 3.6B active (MoE)
Attention: Sliding-window attention
Max context: 131,072 tokens
Released: 2025-08-05
Model card: gpt-oss-20b on Hugging Face

GGUF files

Tracked quantizations of gpt-oss-20b, smallest first
Quant	File size	Quality	Published by
MXFP4baseline	12.11 GB	Near-lossless	llama.cpp team · ggml-org

Memory needed by quant and context

Weights + f16 KV cache + compute buffer, in GB. Add about 0.6 GB if the GPU also drives your display on Windows.
Quant	4k	8k	16k	32k	64k	128k
MXFP4	12.7	12.9	13.2	13.7	14.8	17.0

Which GPUs can run gpt-oss-20b?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Sort

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at MXFP4 with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs greatDetails	282.3 tok/s8k estimate 235.0 tok/s (188.0–282.0, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 32.0 GB	Full GPU	up to 128k	—	$4,200 street (as of 2026-08-09)
GeForce RTX 4090	Runs greatDetails	225.2 tok/s8k estimate 198.3 tok/s (158.7–238.0, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 24.0 GB	Full GPU	up to 128k	—	$2,755 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 209.9 tok/s167.9–251.8calibrated estimate ±20%	MXFP4	13.5 / 24.0 GB	Full GPU	up to 128k	—	$999 launch MSRP
GeForce RTX 5080	Runs great	204.9 tok/s8k estimate 188.9 tok/s (151.1–226.6, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$1,256 street (as of 2026-08-09)
GeForce RTX 3090 Ti	Runs great	est. 198.3 tok/s158.7–238.0calibrated estimate ±20%	MXFP4	13.5 / 24.0 GB	Full GPU	up to 128k	—	$1,999 launch MSRP
GeForce RTX 5070 Ti	Runs great	189.5 tok/s8k estimate 176.3 tok/s (141.0–211.5, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$949 street (as of 2026-08-09)
GeForce RTX 4080 Super	Runs great	186.4 tok/s8k estimate 144.8 tok/s (115.8–173.8, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$999 launch MSRP
GeForce RTX 5080 Laptop	Runs great	est. 176.3 tok/s141.0–211.5calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	—
GeForce RTX 5090 Laptop	Runs great	est. 176.3 tok/s141.0–211.5calibrated estimate ±20%	MXFP4	13.5 / 24.0 GB	Full GPU	up to 128k	—	—
GeForce RTX 3090	Runs greatDetails	162.0 tok/s8k estimate 184.2 tok/s (147.3–221.0, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 24.0 GB	Full GPU	up to 128k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 4080	Runs great	est. 141.1 tok/s112.9–169.3calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$1,199 launch MSRP
Radeon RX 9070	Runs great	est. 141.0 tok/s112.8–169.2calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs great	est. 141.0 tok/s112.8–169.2calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$689 street (as of 2026-08-09)
Radeon RX 7800 XT	Runs great	est. 136.4 tok/s109.1–163.7calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$499 launch MSRP
GeForce RTX 4070 Ti Super	Runs great	est. 132.2 tok/s105.8–158.7calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$799 launch MSRP
Apple M3 Ultra · 96 GB	Runs great	115.5 tok/s8k estimate 103.8 tok/s (83.1–124.6, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	12.9 / 67.2 GB	Unified memory	up to 128k	—	—
GeForce RTX 4090 Laptop	Runs great	est. 113.3 tok/s90.7–136.0calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	—
GeForce RTX 5060 Ti 16GB	Runs greatDetails	111.6 tok/s8k estimate 88.1 tok/s (70.5–105.8, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$569 street (as of 2026-08-09)
Radeon RX 7900 XT	Runs great	101.9 tok/s8k estimate 174.9 tok/s (139.9–209.9, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	13.5 / 20.0 GB	Full GPU	up to 128k	—	$899 launch MSRP
Apple M2 Ultra · 64 GB	Runs great	est. 101.4 tok/s81.1–121.7calibrated estimate ±20%	MXFP4	12.9 / 44.8 GB	Unified memory	up to 128k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs great	92.4 tok/s8k estimate 71.6 tok/s (57.3–85.9, calibrated estimate ±20%)measured (1 run, 2k context)	MXFP4	12.9 / 33.6 GB	Unified memory	up to 128k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs great	est. 80.5 tok/s64.4–96.6calibrated estimate ±20%	MXFP4	12.9 / 33.6 GB	Unified memory	up to 128k	—	—
Radeon RX 9060 XT 16GB	Runs great	est. 70.4 tok/s56.3–84.5calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$449 street (as of 2026-08-09)
Apple M5 Max (32-core GPU) · 36 GB	Runs great	est. 60.3 tok/s48.3–72.4calibrated estimate ±20%	MXFP4	12.9 / 25.2 GB	Unified memory	up to 64k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs great	est. 59.3 tok/s47.5–71.2calibrated estimate ±20%	MXFP4	12.9 / 22.4 GB	Unified memory	up to 64k	—	$1,999 launch MSRP
GeForce RTX 4060 Ti 16GB	Runs great	est. 56.7 tok/s45.3–68.0calibrated estimate ±20%	MXFP4	13.5 / 16.0 GB	Full GPU	up to 64k	—	$499 launch MSRP
Apple M4 Max (32-core GPU) · 36 GB	Runs great	est. 53.8 tok/s43.0–64.5calibrated estimate ±20%	MXFP4	12.9 / 25.2 GB	Unified memory	up to 64k	—	—
NVIDIA DGX Spark · 128 GB	Runs great	est. 47.7 tok/s38.2–57.3calibrated estimate ±20%	MXFP4	12.9 / 89.6 GB	Unified memory	up to 32k	—	$3,999 launch MSRP
Apple M5 Pro · 24 GB	Runs great	est. 40.3 tok/s32.2–48.3calibrated estimate ±20%	MXFP4	12.9 / 16.8 GB	Unified memory	up to 32k	—	—
Apple M4 Pro · 24 GB	Runs greatDetails	est. 35.8 tok/s28.6–43.0calibrated estimate ±20%	MXFP4	12.9 / 16.8 GB	Unified memory	up to 16k	—	—
Apple M5 · 24 GB	Runs well	est. 20.1 tok/s16.1–24.2calibrated estimate ±20%	MXFP4	12.9 / 16.8 GB	Unified memory	up to 64k	—	—
Apple M4 · 24 GB	Runs wellDetails	est. 15.7 tok/s12.6–18.9calibrated estimate ±20%	MXFP4	12.9 / 16.8 GB	Unified memory	up to 32k	—	—
Intel Arc B580	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$290 street (as of 2026-08-09)
GeForce GTX 1080 Ti	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 11.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$699 launch MSRP
GeForce RTX 2080 Ti	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 11.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$999 launch MSRP
GeForce RTX 3050 8GB	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$249 launch MSRP
GeForce RTX 3060 12GB	Runs slowlyDetails	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$250 street (as of 2026-08-09)
GeForce RTX 3070	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$499 launch MSRP
GeForce RTX 3080 10GB	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 10.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$699 launch MSRP
GeForce RTX 3080 12GB	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$799 launch MSRP
GeForce RTX 4060	Runs slowlyDetails	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$299 launch MSRP
GeForce RTX 4060 Laptop	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	—
GeForce RTX 4060 Ti 8GB	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$399 launch MSRP
GeForce RTX 4070	Runs slowlyDetails	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$599 launch MSRP
GeForce RTX 4070 Laptop	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	—
GeForce RTX 4070 Super	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$599 launch MSRP
GeForce RTX 4080 Laptop	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	—
GeForce RTX 5060	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 8.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$429 street (as of 2026-08-09)
GeForce RTX 5070	Runs slowlyDetails	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs slowly	est. 18.5 tok/s12.9–24.0theoretical estimate ±30%	MXFP4	2.0 / 12.0 GB + 11.5 GB RAM	MoE experts in RAM	up to 128k	Experts run from system RAM — Runs well needs 30 tok/s or more on this path	—
DDR5-6000 dual-channel CPU · 32 GB	Runs slowly	est. 18.0 tok/s14.4–21.7calibrated estimate ±20%	MXFP4	12.3 GB RAM	CPU only	up to 128k	CPU inference — capped at Runs slowly	—
DDR5-5600 dual-channel CPU · 32 GB	Runs slowly	est. 16.8 tok/s13.5–20.2calibrated estimate ±20%	MXFP4	12.3 GB RAM	CPU only	up to 128k	CPU inference — capped at Runs slowly	—
DDR4-3200 dual-channel CPU · 32 GB	Runs slowly	est. 9.6 tok/s7.7–11.6calibrated estimate ±20%	MXFP4	12.3 GB RAM	CPU only	up to 128k	—	—

Reasoning models spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s).

Cheapest GPUs that run it

Runs greatRadeon RX 9060 XT 16GB$449 street (as of 2026-08-09), est. 70.4 tok/s (56.3–84.5, calibrated estimate ±20%).

Measured results for gpt-oss-20b

Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.

Measured results for gpt-oss-20b
Hardware	Quant	Backend	Context	Prompt (tok/s)	Generation (tok/s)	Flags	Source	Measured
GeForce RTX 5090	MXFP4	llama.cpp	2k	9,841.0	282.3	—	github.com	2025-08-15
GeForce RTX 4090	MXFP4	llama.cpp	2k	8,078.0	225.2	—	github.com	2025-08-15
GeForce RTX 5080	MXFP4	llama.cpp	2k	7,469.0	204.9	—	github.com	2025-08-15
GeForce RTX 5070 Ti	MXFP4	llama.cpp	2k	6,326.0	189.5	—	github.com	2025-08-15
GeForce RTX 4080 Super	MXFP4	llama.cpp	2k	8,111.0	186.4	—	github.com	2025-08-15
GeForce RTX 3090	MXFP4	llama.cpp	2k	5,143.0	162.0	—	github.com	2025-08-15
GeForce RTX 5060 Ti 16GB	MXFP4	llama.cpp	2k	3,821.0	111.6	—	github.com	2025-08-15
Radeon RX 7900 XT	MXFP4	llama.cpp	2k	4,252.0	101.9	ROCm	github.com	2025-08-15
Apple M3 Ultra	MXFP4	llama.cpp	2k	2,816.0	115.5	—	github.com	2025-08-15
Apple M4 Max (40-core GPU)	MXFP4	llama.cpp	2k	1,277.0	92.4	—	github.com	2025-08-15

Frequently asked questions

How much VRAM does gpt-oss-20b need?

At MXFP4 the weights are 12.11 GB; with 8k context the total is about 12.9 GB (KV cache 0.2 GB, compute buffer 0.6 GB).

What is the cheapest GPU that runs gpt-oss-20b well?

Cheapest that runs it great: Radeon RX 9060 XT 16GB at $449 (street price as of 2026-08-09), est. 70.4 tok/s (56.3–84.5, calibrated estimate ±20%).

Can gpt-oss-20b run on an 8 GB, 16 GB or 24 GB GPU?

At MXFP4 with 8k context: GeForce RTX 4060 — Runs slowly, est. 18.5 tok/s (12.9–24.0, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs great, 111.6 tok/s measured at 2k context (1 run; 8k estimate 88.1 tok/s, 70.5–105.8, calibrated estimate ±20%); GeForce RTX 3090 — Runs great, 162.0 tok/s measured at 2k context (1 run; 8k estimate 184.2 tok/s, 147.3–221.0, calibrated estimate ±20%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.