Skip to content

Best GPU for gpt-oss-20b: VRAM Requirements

gpt-oss-20b needs about 46.4 GB of GPU memory in BF16 and 11.9 GB at 4 bits. See which GPUs fit it for inference and fine-tuning.

gpt-oss-20b needs about 46.4 GB of VRAM in FP16, 23.4 GB in FP8 and 11.9 GB at 4 bits for inference with an 8,192-token context. In FP16 it fits on one NVIDIA A100 PCIe 80GB; a 4-bit build fits on one NVIDIA GeForce RTX 5080 16GB. Its weights are published in 4-bit MXFP4, so the 4-bit figure is the closest to the checkpoint.

gpt-oss-20b is a mixture-of-experts language model with 20.9B total and 3.6B active parameters per token from OpenAI, released in August 2025, with a 131,072-token context window and published under the Apache 2.0. Its weights alone take 41.8 GB in BF16 and 10.5 GB at 4 bits per parameter; the tables below add the KV cache and runtime memory, then list the GPUs that hold each setup.

Recommended GPUs for gpt-oss-20b

gpt-oss-20b VRAM requirements by precision

One request with an 8,192-token context, KV cache in BF16, plus a 10 % margin for activations and runtime buffers.

PrecisionWeightsKV cacheTotal for inference
BF16 / FP1641.8 GB0.4 GB46.4 GB
FP820.9 GB0.4 GB23.4 GB
INT4 (closest to published MXFP4)10.5 GB0.4 GB11.9 GB

gpt-oss-20b VRAM by task

Fine-tuning rows assume a short sequence, batch 1 and gradient checkpointing; longer sequences add activation memory.

TaskGPU memory
Inference at the full 131,072-token context (FP8)30.1 GB
QLoRA (4-bit base)13.6 GB
LoRA (BF16 base)54.3 GB
Full fine-tuning (BF16, AdamW)367.8 GB

GPUs that fit gpt-oss-20b

Number of cards whose combined memory holds each setup, assuming the model is split across them with tensor or pipeline parallelism. A dash means more than eight cards.

GPUMemoryBF16 inference (46.4 GB)FP8 inference (23.4 GB)INT4 inference (11.9 GB)QLoRA (13.6 GB)LoRA (54.3 GB)
NVIDIA GeForce RTX 5080 16GB16 GB4 GPUs2 GPUs1 GPU1 GPU4 GPUs
NVIDIA GeForce RTX 4090 24GB24 GB2 GPUs1 GPU1 GPU1 GPU4 GPUs
NVIDIA L4 24GB24 GB2 GPUs1 GPU1 GPU1 GPU4 GPUs
NVIDIA GeForce RTX 5090 32GB32 GB2 GPUs1 GPU1 GPU1 GPU2 GPUs
NVIDIA Tesla V100 32GB32 GB2 GPUs1 GPU1 GPU1 GPU2 GPUs
NVIDIA A100 PCIe 40GB40 GB2 GPUs1 GPU1 GPU1 GPU2 GPUs
NVIDIA L40S 48GB48 GB1 GPU1 GPU1 GPU1 GPU2 GPUs
NVIDIA Quadro RTX 8000 48GB48 GB1 GPU1 GPU1 GPU1 GPU2 GPUs
NVIDIA RTX 6000 Ada 48GB48 GB1 GPU1 GPU1 GPU1 GPU2 GPUs
NVIDIA RTX A6000 48GB48 GB1 GPU1 GPU1 GPU1 GPU2 GPUs
NVIDIA A100 PCIe 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA A100 SXM 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H100 PCIe 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H100 SXM 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA RTX PRO 6000 Blackwell 96GB96 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H200 141GB141 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA B200 180GB180 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA B300 288GB288 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA GB300 NVL288 GB1 GPU1 GPU1 GPU1 GPU1 GPU

What is gpt-oss-20b?

gpt-oss-20b is the smaller of OpenAI's open-weight reasoning models: a mixture-of-experts model with 3.6 billion active parameters per token. Its expert weights ship in the 4-bit MXFP4 format, and OpenAI states that it runs within 16 GB of memory.

Developer
OpenAI
Released
August 2025
Parameters
20.9B total, 3.6B active per token
Context window
131,072 tokens
License
Apache 2.0

Expert weights are MXFP4 (about 4.25 bits per parameter) and attention weights BF16, so the 4-bit row is the closest to the published checkpoint, which takes about 13.8 GB, more than the 4-bit weight estimate. Half of the layers use a 128-token sliding window, which keeps the real KV cache below this estimate.

Source: gpt-oss-20b model card (as of November 17, 2026).

Frequently asked questions

How much VRAM does gpt-oss-20b need?
For inference with an 8,192-token context and one request, gpt-oss-20b needs about 46.4 GB in BF16, 23.4 GB in FP8, 11.9 GB in INT4, including a 10 % runtime margin. Real usage depends on the inference engine and its settings.
Can gpt-oss-20b run on a single GPU?
Yes. In BF16 it needs about 46.4 GB, which fits one NVIDIA A100 PCIe 80GB (80 GB).
How much GPU memory does fine-tuning gpt-oss-20b take?
QLoRA (4-bit base): about 13.6 GB; LoRA (BF16 base): about 54.3 GB; Full fine-tuning (BF16, AdamW): about 367.8 GB. Longer training sequences and larger batches add activation memory on top.
What is the best GPU for gpt-oss-20b?
Best for inference: 1 GPU × NVIDIA L4 24GB (4-bit weights, 11.9 GB at 8,192 tokens). Best for fine-tuning: 1 GPU × NVIDIA A100 PCIe 80GB (LoRA on BF16 weights, 54.3 GB). Budget pick: 1 GPU × NVIDIA GeForce RTX 5080 16GB (Smallest card class that holds a 4-bit build, 11.9 GB). Check live offers before booking, as availability changes.
Can gpt-oss-20b run on an RTX 4090?
Yes. In 4-bit it needs about 11.9 GB, which fits one RTX 4090 (24 GB). FP16 needs about 46.4 GB, 2 of these cards.
Can gpt-oss-20b run on an RTX 5090?
Yes. In FP8 it needs about 23.4 GB, which fits one RTX 5090 (32 GB). FP16 needs about 46.4 GB, 2 of these cards.

Estimates use the formulas of the LLM VRAM calculator (decimal GB). Real usage depends on the inference engine, quantization format and memory fragmentation: test on the target GPU before a long rental.

Explore the live market

Every offer on the live market comes from a reviewed supplier and is sold by EverXCloud Inc.