Hyperstack - Tutorials

Deploy Qwen3.8 Max on GPU Cloud

Fareed Khan — Thu, 13 Aug 2026 10:46:36 GMT

Qwen3.8 Max is a 2.4 trillion parameter mixture-of-experts model from the Qwen team, and 95 billion of those parameters are awake for any one token. Alibaba put the hosted version in front of developers on 3 August 2026 and published the weights shortly afterwards, which is the first time a Qwen Max class model has been released for anyone to run on their own hardware. The FP8 checkpoint is 2.50 TB across 213 safetensors shards, so a Qwen3.8 Max deployment is a multi-node exercise before it is anything else.

Deploy MiniMax H3 on GPU Cloud

Fareed Khan — Tue, 11 Aug 2026 11:17:46 GMT

MiniMax H3 is a 33 billion parameter omni-modal generative system, open sourced on 3 August 2026, and it does something the text-to-video models before it did not: it writes the soundtrack at the same time as the picture. Video latents and audio latents are predicted by the same transformer, in the same forward pass, from one packed multimodal sequence. What lands on disk is a single MP4 carrying H.264 video at 24 frames per second and AAC stereo at 32 kHz, already in sync, with no separate audio model and no post-production step.

Deploy Kimi K3 on GPU Cloud for Multi-Node 2.8T Inference

Fareed Khan — Tue, 28 Jul 2026 14:38:54 GMT

Kimi K3 is Moonshot AI's 2.8 trillion parameter flagship, and since the weights were published on 27 July 2026 anyone can serve it themselves. It is a sparse Mixture-of-Experts model built on Kimi Delta Attention and Attention Residuals, activating 104 billion parameters through 16 of 896 experts per token, with native vision through MoonViT-V2 and a one million token context window. The checkpoint ships in native MXFP4, and when we pulled it the 96 safetensors shards measured 1,560.94 GB. That one number decides everything about serving it. The official vLLM recipe and the vLLM launch blog both put the floor at Blackwell: at least one 8x NVIDIA B300 node, or an NVIDIA GB300 NVL72, with 16x NVIDIA B200 also supported. NVIDIA H100 is not on that list.

Kimi K3: A Technical Deep Dive into the First Open 3T-Class Model

Fareed Khan — Tue, 21 Jul 2026 13:39:36 GMT

Kimi K3 is the most capable model Moonshot AI has released, a 2.8 trillion parameter system built on two architectural updates, Kimi Delta Attention and Attention Residuals, with native vision and a one million token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work and reasoning, and Moonshot AI has committed to releasing the full model weights by 27 July 2026. In this deep dive, we walk through the architecture, the training and inference infrastructure, the benchmark results and the case studies from the official Kimi K3 release blog, then look at what it takes to be ready to run the model on your own infrastructure the day the weights land.

Deploy Hy3 on GPU Cloud for Multi-Node 295B Inference

Fareed Khan — Fri, 17 Jul 2026 10:52:19 GMT

Tencent Hy3 is an open-weight, hybrid fast-and-slow-thinking model built on a sparse Mixture-of-Experts architecture with 295 billion total parameters, of which only 21 billion activate per token. It routes across 192 experts, carries a native 256K-token context window, ships its weights in BF16 under the Apache 2.0 licence, and scores 90.4 on GPQA Diamond and 72.0 on USAMO 2026. There is one catch that shapes everything about deploying it: the official vLLM recipe states plainly that a single 8x NVIDIA H100-80G node cannot fit it. The BF16 weights alone measure 557 GiB against roughly 637 GiB of VRAM on an 8-GPU NVIDIA H100 node, which leaves about 10 GiB per card to cover the KV cache, the activations and the communication buffers. Hy3 needs two nodes.

How to Use GLM-5.2 on AI Studio

Fareed Khan — Tue, 30 Jun 2026 08:45:34 GMT

Hyperstack AI Studio now serves GLM-5.2, the latest open-weight model from Z.ai (formerly Zhipu AI). It is a reasoning and coding model with a one million token context window, and it is available through the same serverless API and point-and-click Playground you already use for every other model on the platform. There is no GPU to provision, no weights to download and no server to keep warm. You send a list of messages, and you get back a reply.

There are two ways to use it. The Playground is the fastest way to try it by hand, and the API is how you put GLM-5.2 into a product, a coding assistant or an automated pipeline. This guide covers both, with a heavy focus on the API. Every code block in the API section was run against the live endpoint, and the output shown beneath it is the real response.

Generate Stunning AI Images with AI Studio

Fareed Khan — Tue, 23 Jun 2026 08:37:59 GMT

Hyperstack AI Studio can now generate images. Alongside its language models, the platform serves a growing line-up of text-to-image and image-to-image models, including FLUX.1, FLUX.2, Qwen-Image, Stable Diffusion 3.5 and more, behind a single serverless API and a point-and-click Playground. There is no GPU to rent, no container to build and no model to download. You send a prompt, and you get back an image.

There are two ways to use it. The Playground is the fastest way to experiment by hand, and the API is how you put image generation into a product or an automated pipeline. This guide covers both, with a heavy focus on the API. Each section pairs a runnable code block with the image it produces, so you can follow along and generate the same results on Hyperstack AI Studio.

Deploy DiffusionGemma on a Cloud GPU

Fareed Khan — Fri, 12 Jun 2026 08:44:49 GMT

What is DiffusionGemma?

DiffusionGemma is an open-weights, diffusion-based language model built by Google DeepMind on the 26B-A4B Mixture-of-Experts Gemma 4 architecture. Instead of generating text one token at a time, DiffusionGemma generates a whole block of tokens in parallel using discrete diffusion. It carries 25.2B total parameters while activating only 3.8B parameters during inference. It accepts interleaved text, image, and video input to produce text output, and it ships under the Apache 2.0 license. The headline result is speed. By denoising a 256-token canvas in parallel, DiffusionGemma reaches over 1,000 tokens per second on a single NVIDIA H100, which is roughly 4x the throughput of a comparable autoregressive model.

How to Optimise the KV Cache: A Guide to Faster, Cheaper LLM Inference

Fareed Khan — Wed, 10 Jun 2026 04:15:01 GMT

Serving LLMs efficiently comes down, again and again, to one component: the KV cache. After the model weights themselves, it is the single biggest consumer of NVIDIA GPU memory during inference, and it is the reason long contexts and large batches get expensive fast.

How to Run Distributed Inference with vLLM

Fareed Khan — Tue, 02 Jun 2026 09:47:19 GMT

LLMs have outgrown single GPUs. A 70B model in 16-bit precision needs roughly 140 GB just for weights, more than fits on any single 80 GB card, and that is before you reserve a single byte for the KV cache that serves requests. The moment you try, vLLM greets you with the most familiar error in the field: CUDA out of memory.