Model Library/gpt-oss-20b

OpenAI

gpt-oss-20b

The small GPT-OSS model, for fast single-user chat.

TextvLLMllama.cpp3 builds

Recommended: RTX 5090, 32 GB GDDR7, $0.69 / hour, billed per minute. Check availability.

Configure

Every build below is published on Hugging Face and fits at least one GPU we rent. Pick the quantization and engine: the memory it needs, the GPUs it fits and the recommended GPU follow, and Deploy takes that exact build, revision and GPU to the console. Only the one-click preset is tested by GPUwerk.

gpt-oss-20b, MXFP4 on vLLM
QuantizationMXFP4
EnginevLLM
StatusUntested by GPUwerk
Weights13.8 GB
GPU memory it needsAbout 18.9 GB with a 32k-token cache, an estimate
Recommended GPURTX 5090, $0.69 / hour
Weights sourceopenai/gpt-oss-20b, revision 6cee5e81ee83
Licence on the cardapache-2.0
GPUs gpt-oss-20b MXFP4 does and does not fit
GPUMemoryPriceAvailabilityDeploy
RTX 5090x86 · Blackwell · recommended32 GB GDDR7$0.69 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on RTX 5090
DGX SparkArm · GB10128 GB unified$0.79 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on DGX Spark
RTX PRO 6000x86 · Blackwell96 GB GDDR7$1.89 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on RTX PRO 6000
H100 SXMx86 · Hopper80 GB HBM3$2.69 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on H100 SXM
H200x86 · Hopper141 GB HBM3e$3.49 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on H200
B200x86 · Blackwell180 GB HBM3e$5.49 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on B200
B300x86 · Blackwell288 GB HBM3e$6.49 / hourCheck availabilityRun it yourself gpt-oss-20b MXFP4 on B300

Builds by the model's maker, NVIDIA and Unsloth, read from Hugging Face on 21 November 2026. Memory is an estimate (weights x 1.15 plus 3 GB); GGUF runs on llama.cpp, which GPUwerk builds for the DGX Spark only, and NVFP4 needs a Blackwell GPU. SGLang is not offered: there is no SGLang runtime yet.

Details

About the model.

gpt-oss-20b
MakerOpenAI
TaskText
Parameters21B total, 3.6B active (mixture of experts)
LicenceApache 2.0

No speed figure here: GPUwerk lists only figures it measured itself. Reported figures, with their sources, are in the model guide.

Quick start

  1. Deploy a DGX Spark with a base image (DGX OS or Ubuntu).
  2. Follow the gpt-oss-20b guide to download the weights and start llama.cpp.
  3. Connect over SSH or the browser terminal; the machine is yours until you terminate it.

SSH, the browser terminal, VNC and your workspace work the same on every instance. Terminate when you are done and billing ends.

Related models

QwenCoding · Text

Qwen3 Coder 30B

A coding model for agents and editors, with tool calls turned on.

One-click preset · vLLM · RTX 5090

QwenText

Qwen3.6 35B-A3B

A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.

One-click preset · llama.cpp · DGX Spark

OpenAIText

GPT-OSS 120B

OpenAI's open-weight 120B model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

All models in the library