gpt-oss-120b

Gpt family · 117.0B params

1recorded run

223.4best tok/s

1verified

Evidence: 1 sourced run · 1 independent source · first recorded May 16, 2026. What these labels mean.

What the gpt-oss-120b numbers mean

The fastest verified result on our board is 223.4 output tok/s on an Radeon AI Pro R9700 x3 at MXFP4 with a 32768-token context. That is about 4.5 ms per generated token — 500 tokens takes roughly 2.2 seconds.

How much VRAM does gpt-oss-120b need?

gpt-oss-120b has 117.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Quantisation	Estimated VRAM	Smallest card that fits
Q4_K_M (4-bit)	76.5 GB	96 GB
Q8_0 (8-bit)	143.8 GB	192 GB
FP16 (16-bit)	269.9 GB	multi-GPU or CPU offload

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Fastest GPUs for this model (best tok/s)

Radeon AI Pro R9700 x3223.4

Models with a similar footprint

Model	Params	Q4_K_M weights
Laguna-S-2.1	118B	66.4 GB
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	120B	67.5 GB
Llama-4-Scout-17B-16E-Instruct	109B	61.3 GB
Qwen 3.8 Flash	125B	70.3 GB
Qwen 3.8 Flash-Next Base	125B	70.3 GB
Ling-3.0-flash	127B	71.4 GB

Ranked by distance from gpt-oss-120b's parameter count. Full benchmark board.

All benchmarks Methodology

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Radeon AI Pro R9700 x3 · 32 GB	gpt-oss-120b	MXFP4	vllm 0.20.2+rocm-mxfp4-docker	32768	223.4 ✓	—	—	src