text-embeddings-inference/pr_742/en/supported_models.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Supported models and hardware&quot;,&quot;local&quot;:&quot;supported-models-and-hardware&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported embeddings models&quot;,&quot;local&quot;:&quot;supported-embeddings-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Supported re-rankers and sequence classification models&quot;,&quot;local&quot;:&quot;supported-re-rankers-and-sequence-classification-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Supported hardware&quot;,&quot;local&quot;:&quot;supported-hardware&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/entry/start.40236b54.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/scheduler.6efaaf90.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/singletons.d693fe39.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/paths.8b9dcfff.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/entry/app.339a0f46.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/preload-helper.3da9a969.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/index.eb3e1f0f.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/nodes/0.5cfecfd2.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/nodes/13.44ebbf01.js">
		<link rel="modulepreload" href="/docs/text-embeddings-inference/pr_742/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.bf9a6737.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Supported models and hardware&quot;,&quot;local&quot;:&quot;supported-models-and-hardware&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Supported embeddings models&quot;,&quot;local&quot;:&quot;supported-embeddings-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Supported re-rankers and sequence classification models&quot;,&quot;local&quot;:&quot;supported-re-rankers-and-sequence-classification-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Supported hardware&quot;,&quot;local&quot;:&quot;supported-hardware&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="supported-models-and-hardware" 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-and-hardware"><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 and hardware</span></h1> <p data-svelte-h="svelte-1k6m0ht">We are continually expanding our support for other model types and plan to include them in future updates.</p>  <h2 class="relative group"><a id="supported-embeddings-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-embeddings-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 embeddings models</span></h2> <p data-svelte-h="svelte-aoav01">Text Embeddings Inference currently supports Nomic, BERT, CamemBERT, XLM-RoBERTa models with absolute positions, JinaBERT
model with Alibi positions and Mistral, Alibaba GTE, Qwen2 models with Rope positions, MPNet, ModernBERT, Qwen3, and Gemma3.</p> <p data-svelte-h="svelte-vskdni">Below are some examples of the currently supported models:</p> <table data-svelte-h="svelte-1sce89e"><thead><tr><th>MTEB Rank</th> <th>Model Size</th> <th>Model Type</th> <th>Model ID</th></tr></thead> <tbody><tr><td>2</td> <td>7.57B (Very Expensive)</td> <td>Qwen3</td> <td><a href="https://hf.co/Qwen/Qwen3-Embedding-8B" rel="nofollow">Qwen/Qwen3-Embedding-8B</a></td></tr> <tr><td>3</td> <td>4.02B (Very Expensive)</td> <td>Qwen3</td> <td><a href="https://hf.co/Qwen/Qwen3-Embedding-4B" rel="nofollow">Qwen/Qwen3-Embedding-4B</a></td></tr> <tr><td>4</td> <td>509M</td> <td>Qwen3</td> <td><a href="https://hf.co/Qwen/Qwen3-Embedding-0.6B" rel="nofollow">Qwen/Qwen3-Embedding-0.6B</a></td></tr> <tr><td>6</td> <td>7.61B (Very Expensive)</td> <td>Qwen2</td> <td><a href="https://hf.co/Alibaba-NLP/gte-Qwen2-7B-instruct" rel="nofollow">Alibaba-NLP/gte-Qwen2-7B-instruct</a></td></tr> <tr><td>7</td> <td>560M</td> <td>XLM-RoBERTa</td> <td><a href="https://hf.co/intfloat/multilingual-e5-large-instruct" rel="nofollow">intfloat/multilingual-e5-large-instruct</a></td></tr> <tr><td>8</td> <td>308M</td> <td>Gemma3</td> <td><a href="https://hf.co/google/embeddinggemma-300m" rel="nofollow">google/embeddinggemma-300m</a> (gated)</td></tr> <tr><td>15</td> <td>1.78B (Expensive)</td> <td>Qwen2</td> <td><a href="https://hf.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct" rel="nofollow">Alibaba-NLP/gte-Qwen2-1.5B-instruct</a></td></tr> <tr><td>18</td> <td>7.11B (Very Expensive)</td> <td>Mistral</td> <td><a href="https://hf.co/Salesforce/SFR-Embedding-2_R" rel="nofollow">Salesforce/SFR-Embedding-2_R</a></td></tr> <tr><td>35</td> <td>568M</td> <td>XLM-RoBERTa</td> <td><a href="https://hf.co/Snowflake/snowflake-arctic-embed-l-v2.0" rel="nofollow">Snowflake/snowflake-arctic-embed-l-v2.0</a></td></tr> <tr><td>41</td> <td>305M</td> <td>Alibaba GTE</td> <td><a href="https://hf.co/Snowflake/snowflake-arctic-embed-m-v2.0" rel="nofollow">Snowflake/snowflake-arctic-embed-m-v2.0</a></td></tr> <tr><td>52</td> <td>335M</td> <td>BERT</td> <td><a href="https://hf.co/WhereIsAI/UAE-Large-V1" rel="nofollow">WhereIsAI/UAE-Large-V1</a></td></tr> <tr><td>58</td> <td>137M</td> <td>NomicBERT</td> <td><a href="https://hf.co/nomic-ai/nomic-embed-text-v1" rel="nofollow">nomic-ai/nomic-embed-text-v1</a></td></tr> <tr><td>79</td> <td>137M</td> <td>NomicBERT</td> <td><a href="https://hf.co/nomic-ai/nomic-embed-text-v1.5" rel="nofollow">nomic-ai/nomic-embed-text-v1.5</a></td></tr> <tr><td>103</td> <td>109M</td> <td>MPNet</td> <td><a href="https://hf.co/sentence-transformers/all-mpnet-base-v2" rel="nofollow">sentence-transformers/all-mpnet-base-v2</a></td></tr> <tr><td>N/A</td> <td>475M-A305M</td> <td>NomicBERT</td> <td><a href="https://hf.co/nomic-ai/nomic-embed-text-v2-moe" rel="nofollow">nomic-ai/nomic-embed-text-v2-moe</a></td></tr> <tr><td>N/A</td> <td>434M</td> <td>Alibaba GTE</td> <td><a href="https://hf.co/Alibaba-NLP/gte-large-en-v1.5" rel="nofollow">Alibaba-NLP/gte-large-en-v1.5</a></td></tr> <tr><td>N/A</td> <td>396M</td> <td>ModernBERT</td> <td><a href="https://hf.co/answerdotai/ModernBERT-large" rel="nofollow">answerdotai/ModernBERT-large</a></td></tr> <tr><td>N/A</td> <td>340M</td> <td>Qwen3</td> <td><a href="https://hf.co/voyageai/voyage-4-nano" rel="nofollow">voyageai/voyage-4-nano</a></td></tr> <tr><td>N/A</td> <td>137M</td> <td>JinaBERT</td> <td><a href="https://hf.co/jinaai/jina-embeddings-v2-base-en" rel="nofollow">jinaai/jina-embeddings-v2-base-en</a></td></tr> <tr><td>N/A</td> <td>137M</td> <td>JinaBERT</td> <td><a href="https://hf.co/jinaai/jina-embeddings-v2-base-code" rel="nofollow">jinaai/jina-embeddings-v2-base-code</a></td></tr></tbody></table> <p data-svelte-h="svelte-1fz6qfa">To explore the list of best performing text embeddings models, visit the
<a href="https://huggingface.co/spaces/mteb/leaderboard" rel="nofollow">Massive Text Embedding Benchmark (MTEB) Leaderboard</a>.</p>  <h2 class="relative group"><a id="supported-re-rankers-and-sequence-classification-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-re-rankers-and-sequence-classification-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 re-rankers and sequence classification models</span></h2> <p data-svelte-h="svelte-17enjvk">Text Embeddings Inference currently supports CamemBERT, and XLM-RoBERTa Sequence Classification models with absolute positions.</p> <p data-svelte-h="svelte-vskdni">Below are some examples of the currently supported models:</p> <table data-svelte-h="svelte-1lqpwl"><thead><tr><th>Task</th> <th>Model Type</th> <th>Model ID</th></tr></thead> <tbody><tr><td>Re-Ranking</td> <td>XLM-RoBERTa</td> <td><a href="https://huggingface.co/BAAI/bge-reranker-large" rel="nofollow">BAAI/bge-reranker-large</a></td></tr> <tr><td>Re-Ranking</td> <td>XLM-RoBERTa</td> <td><a href="https://huggingface.co/BAAI/bge-reranker-base" rel="nofollow">BAAI/bge-reranker-base</a></td></tr> <tr><td>Re-Ranking</td> <td>GTE</td> <td><a href="https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base" rel="nofollow">Alibaba-NLP/gte-multilingual-reranker-base</a></td></tr> <tr><td>Re-Ranking</td> <td>ModernBert</td> <td><a href="https://huggingface.co/Alibaba-NLP/gte-reranker-modernbert-base" rel="nofollow">Alibaba-NLP/gte-reranker-modernbert-base</a></td></tr> <tr><td>Sentiment Analysis</td> <td>RoBERTa</td> <td><a href="https://huggingface.co/SamLowe/roberta-base-go_emotions" rel="nofollow">SamLowe/roberta-base-go_emotions</a></td></tr></tbody></table>  <h2 class="relative group"><a id="supported-hardware" 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-hardware"><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 hardware</span></h2> <p data-svelte-h="svelte-v5c6kt">Text Embeddings Inference supports can be used on CPU, Turing (T4, RTX 2000 series, …), Ampere 80 (A100, A30),
Ampere 86 (A10, A40, …), Ada Lovelace (RTX 4000 series, …), Hopper (H100), and Blackwell (B200, …) architectures.</p> <p data-svelte-h="svelte-1l2nroq">The library does <strong>not</strong> support CUDA compute capabilities &lt; 7.5, which means V100, Titan V, GTX 1000 series, etc. are not supported.</p> <p data-svelte-h="svelte-j76380">To leverage your GPUs, make sure to install the
<a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html" rel="nofollow">NVIDIA Container Toolkit</a>, and use
NVIDIA drivers with CUDA version 12.2 or higher.</p> <p data-svelte-h="svelte-16dfo8x">Find the appropriate Docker image for your hardware in the following table:</p> <table data-svelte-h="svelte-1r6m5vr"><thead><tr><th>Architecture</th> <th>Image</th></tr></thead> <tbody><tr><td>CPU</td> <td>ghcr.io/huggingface/text-embeddings-inference:cpu-1.9</td></tr> <tr><td>Volta</td> <td>NOT SUPPORTED</td></tr> <tr><td>Turing (T4, RTX 2000 series, …)</td> <td>ghcr.io/huggingface/text-embeddings-inference:turing-1.9 (experimental)</td></tr> <tr><td>Ampere 8.0 (A100, A30)</td> <td>ghcr.io/huggingface/text-embeddings-inference:1.9</td></tr> <tr><td>Ampere 8.6 (A10, A40, …)</td> <td>ghcr.io/huggingface/text-embeddings-inference:86-1.9</td></tr> <tr><td>Ada Lovelace (RTX 4000 series, …)</td> <td>ghcr.io/huggingface/text-embeddings-inference:89-1.9</td></tr> <tr><td>Hopper (H100)</td> <td>ghcr.io/huggingface/text-embeddings-inference:hopper-1.9</td></tr> <tr><td>Blackwell 10.0 (B200, GB200, …)</td> <td>ghcr.io/huggingface/text-embeddings-inference:100-1.9 (experimental)</td></tr> <tr><td>Blackwell 12.0 (GeForce RTX 50X0, …)</td> <td>ghcr.io/huggingface/text-embeddings-inference:120-1.9 (experimental)</td></tr></tbody></table> <p data-svelte-h="svelte-173bv05"><strong>Warning</strong>: Flash Attention is turned off by default for the Turing image as it suffers from precision issues.
You can turn Flash Attention v1 ON by using the <code>USE_FLASH_ATTENTION=True</code> environment variable.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/text-embeddings-inference/blob/main/docs/source/en/supported_models.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1f4ry9h = {
						assets: "/docs/text-embeddings-inference/pr_742/en",
						base: "/docs/text-embeddings-inference/pr_742/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/text-embeddings-inference/pr_742/en/_app/immutable/entry/start.40236b54.js"),
						import("/docs/text-embeddings-inference/pr_742/en/_app/immutable/entry/app.339a0f46.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 13],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>