docs: FrogNano-4B-2609 on Runpod Serverless

docs.json

@@ -62,7 +62,7 @@
               "get-started",
               "get-started/connect-to-runpod",
               "get-started/concepts",
-              "get-started/credentials",              
+              "get-started/credentials",
               "get-started/agent-skills",
               "get-started/mcp-servers",
               "get-started/early-access"
@@ -238,7 +238,7 @@
               }
             ]
           },
-                    {
+          {
             "group": "Storage",
             "pages": [
               "storage/network-volumes",
@@ -248,7 +248,7 @@
                 "group": "Global volumes (Beta)",
                 "pages": [
                   "storage/globalvolume/overview",
-                  "storage/globalvolume/globalvolume-pods"                  
+                  "storage/globalvolume/globalvolume-pods"
                 ]
               }
             ]
@@ -724,7 +724,8 @@
             "pages": [
               "public-endpoints/models/granite-4",
               "public-endpoints/models/moonshot-kimi",
-              "public-endpoints/models/qwen3-32b"
+              "public-endpoints/models/qwen3-32b",
+              "public-endpoints/models/microsoft-frognano-4b-2609"
             ]
           },
           {

public-endpoints/models/microsoft-frognano-4b-2609.mdx

@@ -0,0 +1,43 @@
+---
+title: "FrogNano-4B-2609"
+sidebarTitle: "FrogNano-4B-2609"
+description: "Deploy Microsoft FrogNano-4B-2609 on Runpod Serverless with vLLM, fp8 precision, and an 8,192 token max model length."
+---
+
+## Overview
+
+FrogNano-4B-2609 is a 4B parameter text model from Microsoft, published as `microsoft/frognano-4b-2609`. This recipe serves it on Runpod Serverless with vLLM on a single GPU, so you can run long multi-turn, tool-calling agent workloads yourself instead of paying per token.
+
+## Recipe
+
+| Setting | Value |
+| --- | --- |
+| Engine | vllm |
+| Image | `runpod/worker-v1-vllm:v2.27.0` |
+| GPU | 1x RTX 4090 |
+| Precision | fp8 |
+| Max model length | 8,192 |
+
+## Deploy
+
+Deploy the template from the console: [Deploy FrogNano-4B-2609](https://console.runpod.io/deploy?template=902q8tlzie&utm_source=docs&utm_medium=content&utm_campaign=202610_activation_indie-ml-dev_microsoft-frognano-4b-2609&utm_content=model-page)
+
+```bash
+runpodctl serverless create --hub-id <vllm listing> --model-reference hf://microsoft/FrogNano-4B-2609
+```
+
+Browse related listings in the [Hub](https://console.runpod.io/hub?utm_source=docs&utm_medium=content&utm_campaign=202610_activation_indie-ml-dev_microsoft-frognano-4b-2609&utm_content=model-page), or [create an account](https://console.runpod.io/signup?utm_source=docs&utm_medium=content&utm_campaign=202610_activation_indie-ml-dev_microsoft-frognano-4b-2609&utm_content=model-page) first.
+
+## Measured performance
+
+| GPU | Price | Throughput | Time to first token | Cold start | Cost per 1M output tokens |
+| --- | --- | --- | --- | --- | --- |
+| 1x RTX 4090, fp8 | $0.69/hr | 104 tokens per second | 582 ms | 870 s | $1.84 |
+
+## Limits
+
+- License: mit. Review the license terms before you deploy.
+- Context length for the model is not stated. This recipe sets a max model length of 8,192, and requests above that limit are rejected.
+- The recipe covers text only. It does not configure a network volume, quantization other than fp8, a custom handler, or multi-GPU serving.
+
+See the [model page](https://www.runpod.io/models/microsoft-frognano-4b-2609?utm_source=docs&utm_medium=content&utm_campaign=202610_activation_indie-ml-dev_microsoft-frognano-4b-2609&utm_content=model-page) and the [deployment walkthrough](https://www.runpod.io/blog/microsoft-frognano-4b-2609-on-runpod-serverless?utm_source=docs&utm_medium=content&utm_campaign=202610_activation_indie-ml-dev_microsoft-frognano-4b-2609&utm_content=model-page).