BTC
ETH
USDT
XMR
LTC
Open model · OpenAI · Apache 2.0
Run gpt-oss-120b
on your own GPUs.
OpenAI reasoning model that fits on a single 80 GB GPU. 117B MoE · 5.1B active parameters, 65 GB of official MXFP4 weights.
- 78 GBGPU memory, MXFP4
- 117B MoE · 5.1B activeparameters
- 1× RTX PRO 6000cheapest server, MXFP4
- $959per month
How much VRAM gpt-oss-120b needs.
Weights × 1.2 for the KV cache and activations, with 92% of GPU memory usable: the rule our deploy page uses. Long contexts and many parallel requests need more.
| Serving option | GPU memory | Cheapest server | Per month | Action |
|---|---|---|---|---|
| vLLM or SGLang, official MXFP4 weights | 78 GB | 1× NVIDIA RTX PRO 6000 | $959/mo | Deploy |
| Ollama + Open WebUI, gpt-oss:120b (quantized) | 78 GB | 1× NVIDIA RTX PRO 6000 | $959/mo | Deploy |
Weights: openai/gpt-oss-120b · 65 GB, MXFP4 · Ollama: gpt-oss:120b, 65 GB. How we estimate GPU memory
Which GPUs run gpt-oss-120b.
Smallest server of each GPU that holds the model, and its monthly price.
| GPU | MXFP4 | Ollama | Price, MXFP4 |
|---|---|---|---|
| NVIDIA B300288 GB HBM3e | 1× | 1× | $4,019/mo |
| NVIDIA B200180 GB HBM3e | 1× | 1× | $3,439/mo |
| AMD MI355X288 GB HBM3E | 1× | 1× | $1,409/mo |
| NVIDIA H200141 GB HBM3e | 1× | 1× | $2,279/mo |
| NVIDIA H10080 GB HBM3 | 2× | 2× | $3,558/mo |
| NVIDIA RTX PRO 600096 GB GDDR7 ECC | 1× | 1× | $959/mo |
| NVIDIA L40S48 GB GDDR6 ECC | 2× | 2× | $1,578/mo |
| NVIDIA RTX 509032 GB GDDR7 | 4× | 4× | $1,316/mo |
| NVIDIA RTX 409024 GB GDDR6X | 4× | 4× | $1,076/mo |
| NVIDIA RTX 508016 GB GDDR7 | — | — | — |
n/a = ROCm support for this model is not confirmed with vLLM or SGLang. — = larger than the biggest server of that GPU. Size another model
Deploy gpt-oss-120b preinstalled.
Pick the model at the Software step of the deploy page: we install it with the engine you choose, at no extra cost.
- 1
Pick the server
The deploy page proposes the cheapest server that holds the model, and switches when you change the precision or the engine.
- 2
Pick the engine
vLLM or SGLang serve an OpenAI-compatible API; Ollama with Open WebUI gives a private chat in the browser.
- 3
Pay and log in
Pay the month in BTC, ETH, USDT, XMR or LTC, no KYC. Your server is online in under 10 minutes after confirmation, with root SSH access.
Guides: serving LLMs with vLLM · GPU servers for LLM inference · first steps on your server
gpt-oss-120b FAQ.
Every model: open models and their VRAM.
How much VRAM does gpt-oss-120b need?
About 78 GB of GPU memory to serve the official MXFP4 weights (65 GB) with vLLM or SGLang, by our rule of weights × 1.2 for the KV cache and activations; about 78 GB with Ollama’s gpt-oss:120b build. Long contexts and many parallel requests need more.
Can gpt-oss-120b run on a single GPU?
Yes, on one B300, B200, MI355X, H200 or RTX PRO 6000 with vLLM or SGLang, official MXFP4 weights, by our sizing rule.
What is the cheapest server for gpt-oss-120b?
The cheapest CryptGPU server for gpt-oss-120b is 1× NVIDIA RTX PRO 6000 at $959 a month, with vLLM or SGLang, official MXFP4 weights. The model can be preinstalled at no extra cost when you order, and you pay in crypto with no KYC.
Does gpt-oss-120b run on the AMD MI355X?
Yes: its support on AMD Instinct GPUs with ROCm is confirmed for vLLM and SGLang, and the MI355X has 288 GB per GPU.
What licence does gpt-oss-120b use?
Apache 2.0. We download the official weights from Hugging Face (openai/gpt-oss-120b); you are responsible for the licence.
Other models to compare.
Your own gpt-oss-120b, ready in minutes.
Dedicated GPUs, one monthly price, the model preinstalled. Paid in crypto, no KYC.