From 85bbdcaba2f160f64eb6232e6dde3f3751ca0304 Mon Sep 17 00:00:00 2001 From: danstotts-ops Date: Fri, 2 Oct 2026 16:49:05 -0600 Subject: [PATCH 1/2] docs: add FrogNano-4B-2609 to the Models tab --- docs.json | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/docs.json b/docs.json index d4b9fe14..fef38b88 100644 --- a/docs.json +++ b/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" ] }, { From b774b1f168d401513ae87931eeeec1a2df2ba2b1 Mon Sep 17 00:00:00 2001 From: danstotts-ops Date: Fri, 2 Oct 2026 16:49:07 -0600 Subject: [PATCH 2/2] docs: FrogNano-4B-2609 on Runpod Serverless (Launch Builder draft) --- .../models/microsoft-frognano-4b-2609.mdx | 43 +++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 public-endpoints/models/microsoft-frognano-4b-2609.mdx diff --git a/public-endpoints/models/microsoft-frognano-4b-2609.mdx b/public-endpoints/models/microsoft-frognano-4b-2609.mdx new file mode 100644 index 00000000..9457f61d --- /dev/null +++ b/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 --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). \ No newline at end of file