> ## Content Index
> Fetch the complete content index at: https://www.motionengineeringtoday.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# ComfyStreamerH3 runs MiniMax H3 video on one RTX 5090 at 448×256
- URL: https://www.motionengineeringtoday.com/comfystreamerh3-runs-minimax-h3-video-on-one-rtx-5090-at-448-256-65/
- Published: 2026-10-15T16:31:19.000Z
- Updated: 2026-10-15T16:31:19.000Z
- Description: Comfy reports 1.28× aggregate throughput in a warm low-resolution run; the published figures do not establish single-clip latency.
- Author: JJ Rooney
- Tags: generative AI video, AI video production, ComfyUI, MiniMax H3

Comfy described ComfyStreamerH3, a ComfyUI node for MiniMax H3 video generation on one 32 GB RTX 5090, in an [8 October 2026 blog post](https://blog.comfy.org/p/how-i-generated-live-video-with-minimax). The experimental workflow targets 448×256-pixel output.

The [project README](https://github.com/Comfy-Org/comfystreamerh3) lists two 15.08-second clips, a median 23.51 seconds across 11 warm RTX 5090 jobs and four-step VSA. Its stated 1.28× real-time figure uses the combined clip duration and measures aggregate throughput. It does not establish single-clip response time or cold-start latency.

Bryan Wade’s post describes combining FastH3 V2 at four sampling steps with sparse attention, a smaller text encoder, pruned and quantized weights, and overlapping decode and encoding. Wade acknowledges artifacts and remaining limits in detail, consistency and resolution. This is low-resolution experimental generation rather than delivery-ready footage.

The managed runtime targets Linux, an Nvidia GPU, Python 3.12 and CUDA 13 PyTorch. The node code is MIT-licensed, but the repository supplies no model weights and third-party components retain their terms. Model licences require separate checking. Motion Engineering Today has not reproduced the benchmark or assessed the output.

AI-assisted, reviewed by **Codex (15-post review authorized by JJ Rooney, 15 October 2026)** on 15 October 2026.