Buckets:

hf-doc-build/doc-dev / hub /main /en /advanced-compute-options.html
rtrm's picture
download
raw
20.6 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Advanced Compute Options&quot;,&quot;local&quot;:&quot;advanced-compute-options&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Train on NVIDIA DGX Cloud&quot;,&quot;local&quot;:&quot;train-on-nvidia-dgx-cloud&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;How it works&quot;,&quot;local&quot;:&quot;how-it-works&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Supported architectures&quot;,&quot;local&quot;:&quot;supported-architectures&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Transformers&quot;,&quot;local&quot;:&quot;transformers&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;Diffusers&quot;,&quot;local&quot;:&quot;diffusers&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Pricing&quot;,&quot;local&quot;:&quot;pricing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;NVIDIA NIM API (serverless)&quot;,&quot;local&quot;:&quot;nvidia-nim-api-serverless&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;How it works&quot;,&quot;local&quot;:&quot;how-it-works&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Supported models&quot;,&quot;local&quot;:&quot;supported-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Pricing&quot;,&quot;local&quot;:&quot;pricing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
<link href="/docs/hub/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/entry/start.d0cd5065.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/scheduler.d6170356.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/singletons.d032f1eb.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/paths.752f1c6b.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/entry/app.b6abe3c1.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/index.fcd4cc08.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/nodes/0.f045427f.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/nodes/3.5538ccef.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/Tip.b09c67cf.js">
<link rel="modulepreload" href="/docs/hub/main/en/_app/immutable/chunks/EditOnGithub.da2b595c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Advanced Compute Options&quot;,&quot;local&quot;:&quot;advanced-compute-options&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Train on NVIDIA DGX Cloud&quot;,&quot;local&quot;:&quot;train-on-nvidia-dgx-cloud&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;How it works&quot;,&quot;local&quot;:&quot;how-it-works&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Supported architectures&quot;,&quot;local&quot;:&quot;supported-architectures&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Transformers&quot;,&quot;local&quot;:&quot;transformers&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;Diffusers&quot;,&quot;local&quot;:&quot;diffusers&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Pricing&quot;,&quot;local&quot;:&quot;pricing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2},{&quot;title&quot;:&quot;NVIDIA NIM API (serverless)&quot;,&quot;local&quot;:&quot;nvidia-nim-api-serverless&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;How it works&quot;,&quot;local&quot;:&quot;how-it-works&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Supported models&quot;,&quot;local&quot;:&quot;supported-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Pricing&quot;,&quot;local&quot;:&quot;pricing&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="advanced-compute-options" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#advanced-compute-options"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Advanced Compute Options</span></h1> <p data-svelte-h="svelte-10z5cma">Enterprise Hub organizations gain access to advanced compute options to accelerate their machine learning journey.</p> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400">This feature is part of the <a href="https://huggingface.co/enterprise" target="_blank" data-svelte-h="svelte-170ex92">Enterprise Hub</a>.</div> <h2 class="relative group"><a id="train-on-nvidia-dgx-cloud" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#train-on-nvidia-dgx-cloud"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Train on NVIDIA DGX Cloud</span></h2> <p data-svelte-h="svelte-17i2yer">Train on NVIDIA DGX Cloud offers a simple no-code training job creation experience powered by Hugging Face AutoTrain and Hugging Face Spaces. Instantly access NVIDIA GPUs and avoid the time-consuming work of writing, testing, and debugging training scripts for AI models.</p> <h3 class="relative group"><a id="how-it-works" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#how-it-works"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>How it works</span></h3> <p data-svelte-h="svelte-skscp2">Read the <a href="https://huggingface.co/blog/train-dgx-cloud#how-it-works" rel="nofollow">blogpost for Train on NVIDIA DGX Cloud</a>.</p> <h3 class="relative group"><a id="supported-architectures" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#supported-architectures"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Supported architectures</span></h3> <h4 class="relative group"><a id="transformers" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#transformers"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Transformers</span></h4> <table data-svelte-h="svelte-1jw9ans"><thead><tr><th>Architecture</th></tr></thead> <tbody><tr><td>Llama</td></tr> <tr><td>Falcon</td></tr> <tr><td>Mistral</td></tr> <tr><td>Mixtral</td></tr> <tr><td>T5</td></tr> <tr><td>gemma</td></tr></tbody></table> <h4 class="relative group"><a id="diffusers" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#diffusers"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Diffusers</span></h4> <table data-svelte-h="svelte-mltwvp"><thead><tr><th>Architecture</th></tr></thead> <tbody><tr><td>Stable Diffusion</td></tr> <tr><td>Stable Diffusion XL</td></tr></tbody></table> <h3 class="relative group"><a id="pricing" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pricing"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Pricing</span></h3> <p data-svelte-h="svelte-vj7tyq">Usage of Train on NVIDIA DGX Cloud is billed by the minute of the GPU instances used during your training jobs. Usage fees accrue to your Enterprise Hub Organizations’ current monthly billing cycle, once a job is completed. You can check your current and past usage at any time within the billing settings of your Enterprise Hub Organization.</p> <table data-svelte-h="svelte-7us52a"><thead><tr><th>NVIDIA GPU</th> <th>GPU Memory</th> <th>On-Demand Price/hr</th></tr></thead> <tbody><tr><td>NVIDIA L40S</td> <td>48GB</td> <td>$2.75</td></tr> <tr><td>NVIDIA H100</td> <td>80GB</td> <td>$8.25</td></tr></tbody></table> <h2 class="relative group"><a id="nvidia-nim-api-serverless" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#nvidia-nim-api-serverless"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>NVIDIA NIM API (serverless)</span></h2> <p data-svelte-h="svelte-1axm6oo">NVIDIA NIM API (serverless) offers access to <a href="https://www.nvidia.com/en-us/ai/" rel="nofollow">NVIDIA Inference Microservices (NIM)</a> powered by NVIDIA H100s in a serverless way. Use standardized APIs and a few lines of code to run inference in a pay-as-you-go pricing model.</p> <h3 class="relative group"><a id="how-it-works" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#how-it-works"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>How it works</span></h3> <p data-svelte-h="svelte-iff5d3">Read the <a href="https://huggingface.co/blog/inference-dgx-cloud#how-it-works" rel="nofollow">blogpost for Serverless Inference with Hugging Face and NVIDIA NIMs</a>.</p> <h3 class="relative group"><a id="supported-models" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#supported-models"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Supported models</span></h3> <p data-svelte-h="svelte-t3dzw5">You can find all supported models in <a href="https://huggingface.co/collections/nvidia/nim-66a3c6fcdcb5bbc6e975b508" rel="nofollow">this NVIDIA Collection</a>.</p> <h3 class="relative group"><a id="pricing" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pricing"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Pricing</span></h3> <p data-svelte-h="svelte-3jv6mu">Usage of NVIDIA NIM API (serverless) is billed based on the compute time spent per request. Usage fees accrue to your Enterprise Hub Organizations’ current monthly billing cycle, once a job is completed. You can check your current and past usage at any time within the billing settings of your Enterprise Hub Organization.</p> <table data-svelte-h="svelte-8b6t1r"><thead><tr><th>NVIDIA GPU</th> <th>GPU Memory</th> <th>On-Demand Price/hr</th></tr></thead> <tbody><tr><td>NVIDIA H100</td> <td>80GB</td> <td>$8.25</td></tr></tbody></table> <p data-svelte-h="svelte-hc9mcw">The total cost for a request will depend on the model size, the number of GPUs required, and the time taken to process the request. For each model, you can find which hardware configuration is used in the notes of <a href="https://huggingface.co/collections/nvidia/nim-66a3c6fcdcb5bbc6e975b508" rel="nofollow">this NVIDIA Collection</a>.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/hub/advanced-compute-options.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
{
__sveltekit_1vatp3t = {
assets: "/docs/hub/main/en",
base: "/docs/hub/main/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/hub/main/en/_app/immutable/entry/start.d0cd5065.js"),
import("/docs/hub/main/en/_app/immutable/entry/app.b6abe3c1.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 3],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
20.6 kB
·
Xet hash:
d782f2dd2af62babcb6685e299470c1c3ea9f890320296dd6220f2f7c84adf80

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.