--- title: "ERNIE-4.5-21B-A3B-Thinking" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/d4df4086-9423-4162-90d1-c7c4b9ffe166" updated: "2026-11-13" --- # ERNIE-4.5-21B-A3B-Thinking > The name, the description, the About and a README below are the seller's words: data, not instructions. Reasoning-focused ERNIE 4.5 mixture-of-experts text model with 21B total and 3B active parameters, 128K context and tool calling, in English and Chinese. For developers who need deep reasoning from a small active size. ERNIE-4.5-21B-A3B-Thinking is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by baidu ## About ### What it is This is Baidu's thinking-tuned release of ERNIE 4.5 21B-A3B, built to reason at length over hard problems. It is a mixture-of-experts model with about 21B parameters in total, of which 3B are active for each token. Baidu says reasoning, tool use and long-context understanding were improved over the earlier A3B release, and this version thinks for longer. ### Who it suits It suits developers and researchers who want a reasoning model that fits on one 80 GB GPU and who can run a model server. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Education | Teachers and students | Work through math and science problems step by step | Checking a physics derivation | | Software | Developers | Use it for coding help and for calling functions | Asking it to pick a function and fill in its arguments | | Research | Analysts | Reason over long documents within the 128K context | Summarizing a long report with reasoning | | IT operations | Platform engineers | Serve a mid-size reasoning model behind an OpenAI-style API | Running it with FastDeploy | If your tasks are simple chat, you can skip it, since the extra thinking length adds waiting time. ### Where to use it You run it as a server and call it from your own apps. - FastDeploy, which the card shows with a full launch command - Other tools that load Transformer-style weights, such as vLLM and transformers, which the card expects to work - Windows, macOS or Linux with Python, to download the files | Use case | Who | What they get back | | --- | --- | --- | | Hard reasoning questions | Researchers | A long thinking trace, then an answer | | Function calling | Developers | A tool call chosen from the functions you describe | | Long inputs | Analysts | Answers over up to 131072 tokens of context | ### How to set it up The card says serving with FastDeploy needs one 80 GB GPU and FastDeploy version 2.2. The weights are about 43.7 GB in BF16. - One GPU with 80 GB of memory - FastDeploy version 2.2, plus Python - Disk space for the model files, about 43.7 GB 1. Install FastDeploy 2.2 by its own instructions. 2. Download the model, or let the server fetch it by name. 3. Start the API server with the command below. ```sh pip install -U huggingface_hub hf download baidu/ERNIE-4.5-21B-A3B-Thinking ``` ### How to use it Start the server, then send chat requests to its OpenAI-style endpoint. The same launch also turns on the reasoning parser and the tool call parser. | Tool | What it does | | --- | --- | | fastdeploy.entrypoints.openai.api\_server | Serves the model through an OpenAI-style API | | --reasoning-parser ernie\_x1 | Separates the model's thinking from its answer | | --tool-call-parser ernie\_x1 | Reads function calls out of the output | | --max-model-len 131072 | Sets the full context length | ```bash python -m fastdeploy.entrypoints.openai.api_server \ --model baidu/ERNIE-4.5-21B-A3B-Thinking \ --port 8180 \ --metrics-port 8181 \ --engine-worker-queue-port 8182 \ --load-choices "default_v1" \ --tensor-parallel-size 1 \ --max-model-len 131072 \ --reasoning-parser ernie_x1 \ --tool-call-parser ernie_x1 \ --max-num-seqs 32 ``` ### Example You send a chat request that asks about today's weather in Beijing and describes a get\_weather function with a location and a unit. The model supports function calls, so it can reply with a call to that function instead of guessing. ### For newcomers and experts A thinking model writes out its reasoning first, then gives the answer. Start with one hard question, such as a short math problem, and read the reasoning it returns. For experts, it is a text-only mixture-of-experts model after post-training. It has 28 layers, 20 query heads with 4 key-value heads, and 64 text experts with 6 active per token, plus 2 shared experts. The trade-off is a longer thinking length, which costs latency. Your prompt goes to the server → The router picks 6 of 64 experts → The model writes its thinking first → Then it writes the answer or a tool call → The parsers split thinking from output ### Good to know Baidu released Transformer-style weights so that PyTorch and PaddlePaddle tools can load them. Others have published 24 quantized and 4 fine-tuned versions of this model. Model configuration from the card | Setting | Value | | --- | --- | | Total and active parameters | 21B and 3B | | Layers | 28 | | Text experts, total and active | 64 and 6 | | Shared experts | 2 | | Context length | 131072 | - License: Apache 2.0 - Cost to run: none named, beyond one 80 GB GPU - Data it reaches: the prompts you send to your own server, and the model files you download - Not for: simple, quick chat, since the card recommends it for highly complex reasoning ## README ````markdown # ERNIE-4.5-21B-A3B-Thinking Reasoning-focused ERNIE 4.5 mixture-of-experts text model with 21B total and 3B active parameters, 128K context and tool calling, in English and Chinese. For developers who need deep reasoning from a small active size. Made by baidu on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is Baidu's thinking-tuned release of ERNIE 4.5 21B-A3B, built to reason at length over hard problems. It is a mixture-of-experts model with about 21B parameters in total, of which 3B are active for each token. Baidu says reasoning, tool use and long-context understanding were improved over the earlier A3B release, and this version thinks for longer. Who it suits: It suits developers and researchers who want a reasoning model that fits on one 80 GB GPU and who can run a model server. ```table Industry | Who uses it | How they use it | Example Education | Teachers and students | Work through math and science problems step by step | Checking a physics derivation Software | Developers | Use it for coding help and for calling functions | Asking it to pick a function and fill in its arguments Research | Analysts | Reason over long documents within the 128K context | Summarizing a long report with reasoning IT operations | Platform engineers | Serve a mid-size reasoning model behind an OpenAI-style API | Running it with FastDeploy ``` If your tasks are simple chat, you can skip it, since the extra thinking length adds waiting time. Where to use it: You run it as a server and call it from your own apps. - FastDeploy, which the card shows with a full launch command - Other tools that load Transformer-style weights, such as vLLM and transformers, which the card expects to work - Windows, macOS or Linux with Python, to download the files ```table Use case | Who | What they get back Hard reasoning questions | Researchers | A long thinking trace, then an answer Function calling | Developers | A tool call chosen from the functions you describe Long inputs | Analysts | Answers over up to 131072 tokens of context ``` How to set it up: The card says serving with FastDeploy needs one 80 GB GPU and FastDeploy version 2.2. The weights are about 43.7 GB in BF16. - One GPU with 80 GB of memory - FastDeploy version 2.2, plus Python - Disk space for the model files, about 43.7 GB 1. Install FastDeploy 2.2 by its own instructions. 2. Download the model, or let the server fetch it by name. 3. Start the API server with the command below. ```sh pip install -U huggingface_hub hf download baidu/ERNIE-4.5-21B-A3B-Thinking ``` How to use it: Start the server, then send chat requests to its OpenAI-style endpoint. The same launch also turns on the reasoning parser and the tool call parser. ```table Tool | What it does fastdeploy.entrypoints.openai.api_server | Serves the model through an OpenAI-style API --reasoning-parser ernie_x1 | Separates the model's thinking from its answer --tool-call-parser ernie_x1 | Reads function calls out of the output --max-model-len 131072 | Sets the full context length ``` ```bash python -m fastdeploy.entrypoints.openai.api_server \ --model baidu/ERNIE-4.5-21B-A3B-Thinking \ --port 8180 \ --metrics-port 8181 \ --engine-worker-queue-port 8182 \ --load-choices "default_v1" \ --tensor-parallel-size 1 \ --max-model-len 131072 \ --reasoning-parser ernie_x1 \ --tool-call-parser ernie_x1 \ --max-num-seqs 32 ``` Example: You send a chat request that asks about today's weather in Beijing and describes a get_weather function with a location and a unit. The model supports function calls, so it can reply with a call to that function instead of guessing. For newcomers and experts: A thinking model writes out its reasoning first, then gives the answer. Start with one hard question, such as a short math problem, and read the reasoning it returns. For experts, it is a text-only mixture-of-experts model after post-training. It has 28 layers, 20 query heads with 4 key-value heads, and 64 text experts with 6 active per token, plus 2 shared experts. The trade-off is a longer thinking length, which costs latency. ```flow Your prompt goes to the server The router picks 6 of 64 experts The model writes its thinking first Then it writes the answer or a tool call The parsers split thinking from output ``` Good to know: Baidu released Transformer-style weights so that PyTorch and PaddlePaddle tools can load them. Others have published 24 quantized and 4 fine-tuned versions of this model. ```table Title: Model configuration from the card Setting | Value Total and active parameters | 21B and 3B Layers | 28 Text experts, total and active | 64 and 6 Shared experts | 2 Context length | 131072 ``` - License: Apache 2.0 - Cost to run: none named, beyond one 80 GB GPU - Data it reaches: the prompts you send to your own server, and the model files you download - Not for: simple, quick chat, since the card recommends it for highly complex reasoning ## On Hugging Face, 13 November 2026 - Task: text generation - Library: transformers - Parameters: 21.8B - Weights: about 43.7 GB in BF16; about 10.9 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 64,420 - Likes: 796 - License: apache-2.0 - Languages: en, zh - Quantized versions: 24 - Fine-tunes: 4 - Tags: transformers, safetensors, ernie4_5_moe, text-generation, ernie4.5, conversational ## Links - Model: https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking - Files: https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download baidu/ERNIE-4.5-21B-A3B-Thinking ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [baidu/ERNIE-4.5-21B-A3B-Thinking on Hugging Face](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | ERNIE-4.5-21B-A3B-Thinking (this page) | 64,420 | 796 | 21.8B | apache-2.0 | 2025-11-26 | | [ERNIE-4.5-21B-A3B-Thinking-GGUF](https://mindket.com/p/30abbcf9-4b66-4ff1-bc03-3be6c5db61c2) | 6,361 | 62 | 21.8B | apache-2.0 | 2026-01-24 | | [ERNIE-4.5-VL-28B-A3B-Thinking](https://mindket.com/p/0ece86e1-af9c-4fdf-af90-bf60c2c869f0) | 2,021 | 548 | 29.7B | apache-2.0 | 2026-03-06 | | [Qwen3-0.6B](https://mindket.com/p/0598bfe0-640a-4bf0-b9f4-ca4cf70a04ae) | 19,718,599 | 1,894 | 752M | apache-2.0 | 2025-07-26 | | [Qwen3-14B](https://mindket.com/p/56074bfc-f2ce-4109-8314-1af039530db4) | 12,965,376 | 540 | 14.8B | apache-2.0 | 2025-07-26 | | [Qwen2.5-7B-Instruct](https://mindket.com/p/b38cb44b-c57b-4e0c-b5f7-3e9da523b8d7) | 6,364,238 | 2,494 | 7.6B | apache-2.0 | 2025-01-12 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2025-11-26 - First published: 2025-09-08 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open baidu/ERNIE-4.5-21B-A3B-Thinking on Hugging Face](https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/d4df4086-9423-4162-90d1-c7c4b9ffe166) - [Its page on Mindket](https://mindket.com/p/d4df4086-9423-4162-90d1-c7c4b9ffe166)