Vast.ai Blog - Plushcap

Blog URL

vast.ai/blog

Posts YTD

38 ↓ vs 47 last year

Avg Posts/Month

4.1 since 2024

Monthly Post Volume

Start year: 2023 2024 2025 2026

Post Details

Search:

Title	Author	Published	Words	HN Pts
Running OpenAI's GPT-OSS on Vast.ai	Team Vast	2025-08-05	1,438	--
Text to Video Generation Using HunyuanVideo on Vast	Team Vast	2025-05-15	964	--
Running Llama 4 Models on Vast.ai	Team Vast	2025-05-04	1,792	--
7 Reasons Why Startups Use Vast.ai	Team Vast	2025-06-05	840	--
Examining the NVIDIA GH200	Team Vast	2024-03-27	834	--
Running RolmOCR on Vast	Team Vast	2025-05-13	969	--
How to Use Unsloth Studio for Fast and Affordable AI Fine-Tuning	Team Vast	2026-05-17	881	--
Open-Source LLMs You Can Train and Deploy on Vast.ai Right Now	Team Vast	2025-07-19	604	--
DeepSeek R1-0528: Enhanced Reasoning with Simplified Thinking Mode on Vast.ai	Team Vast	2025-07-15	984	--
Serving vLLM Embeddings on Vast.ai	Team Vast	2024-09-19	526	--
Structured Outputs with vLLM and Outlines on Vast.ai	Team Vast	2025-01-27	1,081	--
Inside GTC 2026: A Bright Future for AI and GPU Computing	Team Vast	2026-03-31	523	--
Serving DeepSeek Models on Vast.ai with vLLM and Langchain!	Team Vast	2025-02-26	2,119	--
Meta Launches Llama 3.1: A New Era in Open-Source AI	Team Vast	2024-07-25	1,008	--
NVIDIA RTX 4090 vs. A100: Two Powerhouses, Two Purposes	Team Vast	2025-06-02	1,097	--
Security and Compliance at Vast AI	Team Vast	2024-10-17	536	--
Maximizing Value with NVIDIA A40 & RTX A6000 \| June 2024	Team Vast	2024-06-04	1,286	--
Announcing AMD Support	Team Vast	2024-05-02	524	--
What Is a Neocloud? The Business Model Explained	Team Vast	2026-05-26	1,029	--
January Product Update	Team Vast	2024-01-30	946	--
April 2026 Product Update	Team Vast	2026-04-02	722	--
June 2026 Product Update	Team Vast	2026-06-09	648	--
Which NVIDIA RTX 6000 Is Right for You?	Team Vast	2025-11-26	1,358	--
June 2025 Product Update	Team Vast	2025-06-29	459	--
May 2026 Product Update	Team Vast	2026-05-12	860	--
Unsloth Studio Is Now Available on Vast.ai	Team Vast	2026-04-02	203	--
NVIDIA H200 vs. B200: Comparing Datacenter-Grade Accelerators	Team Vast	2025-08-29	1,200	--
H100 vs A100: Comparing Two Powerhouse GPUs	Team Vast	2024-08-23	1,065	--
SEC Filing Analysis Using Mistral Small 3.1's Long Context Window	Team Vast	2025-04-03	2,080	--
How Much Money Can You Earn Renting Out Your GPU on Vast.ai?	Team Vast	2026-05-18	1,208	--
NVIDIA RTX Pro 6000 X Rumors: Blackwell GPU with 96GB VRAM Spotted …	Team Vast	2025-03-18	525	--
Stable Diffusion 3.5: Stability's Most Powerful AI Model Yet	Team Vast	2024-12-09	647	--
The NVIDIA DGX Spark: The New Desktop AI Supercomputer That Fits in …	Team Vast	2025-11-05	747	--
NVIDIA RTX Pro 6000 Blackwell: Redefining the Workstation GPU	Team Vast	2025-05-06	875	--
September 2024 Product Update	Team Vast	2024-09-29	494	--
Mistral Small 4 Just Dropped — Run It on Affordable H200s with …	Team Vast	2026-04-07	753	--
NVIDIA GeForce RTX 5090: Everything You Need to Know	Team Vast	2026-05-21	1,352	--
Starting Smart: Why Spot GPUs Are Ideal for AI Startups	Team Vast	2025-12-05	803	--
Serving Infinity	Team Vast	2024-08-16	816	--
Global Growth of Regional Large Language Models (LLMs)	Team Vast	2025-11-11	1,052	--
Serving Online Inference with TGI on Vast.ai \| June 2024	Team Vast	2024-06-13	489	--
Serving Rerankers on Vast.ai using vLLM	Team Vast	2025-02-19	1,959	--
January & February 2026 Product Updates	Team Vast	2026-02-13	614	--
Vast.ai: Best Video Generation Templates 2025	Team Vast	2025-09-15	747	--
TurboQuant Explained: How It Reduces LLM Memory by 5x and Speeds Up …	Team Vast	2026-05-04	1,447	--
November 2024 Product Update	Team Vast	2024-11-03	473	--
Building Your First MCP Server on Vast.ai	Team Vast	2025-09-09	2,077	--
Deploy LLM Inference Using Vast.ai Serverless	Team Vast	2026-04-20	670	--
Running DeepSeek R1 + Crew AI on Vast.ai	Team Vast	2025-08-19	2,790	--
NVIDIA RTX 5090: Out by Christmas? A Look at the Latest Rumors	Team Vast	2024-10-10	760	--
Introducing the Vast.ai Startup Program	Team Vast	2026-02-06	485	--
High-Performance GPUs for AI: Nvidia RTX 4090 vs AMD Radeon RX 7800 …	Team Vast	2024-02-08	800	--
NVIDIA GeForce RTX 5090: Release Announced	Team Vast	2025-01-08	938	--
NVIDIA RTX 4090 to Be Discontinued Sooner Rather Than Later?	Team Vast	2024-10-27	499	--
Why Choose Vast.ai to Train Custom AI Models	Team Vast	2025-12-04	816	--
Serving sglang on Vast	Team Vast	2024-09-26	816	--
LLMs vs. SLMs: What's the Difference, and Why Does It Matter?	Team Vast	2025-09-20	881	--
Affordable Claude Code Alternative: Run Autonomous Coding Agents on Vast.ai	Team Vast	2026-03-03	465	--
October 2025 Product Update	Team Vast	2025-10-12	980	--
RTX 5090D Faces Uncertainty in China Amid Export Crackdown	Team Vast	2025-05-07	521	--
June 2024 Product Update	Team Vast	2024-06-30	433	--
Vast Product Update \| March 2024	Team Vast	2024-03-02	964	--
GPU-as-a-Service: The Scalable Solution to AI's Compute Crisis	Team Vast	2025-02-14	546	--
Running Deep Cogito on Vast.ai	Team Vast	2025-04-21	1,260	--
Vast.ai Achieves SOC 2 Type II Certification	Team Vast	2025-08-04	743	--
Running Qwen 3.5 Medium Models on Vast.ai	Team Vast	2026-03-06	691	--
Vast.ai's 2025 Year in Review	Team Vast	2025-12-23	449	--
Report: NVIDIA Developing New Blackwell-Based AI Chip for China	Team Vast	2025-09-12	432	--
Wan 2.2 Explained: A New Approach to AI Video Generation	Team Vast	2026-01-27	726	--
New Guide: Deploy MiniMax-M2 on Vast.ai	Team Vast	2025-12-02	552	--
GANs vs. LLMs: What You Need to Know	Team Vast	2025-02-13	1,467	--
India's AI Leap: World's Biggest Data Center on the Horizon?	Team Vast	2025-03-29	635	--
Vast.ai Highlights: 2024 Round-Up	Team Vast	2025-01-07	530	--
Using LLM-Compressor to Quantize Qwen3-8B on Vast.ai (Part 2)	Team Vast	2025-07-22	2,446	--
Less Coding, More Creating: The Rise of Vibe Coding	Team Vast	2025-11-01	727	--
July 2024 Monthly Update: Billing Page Revamp, H100 NVL GPU Addition, and …	Team Vast	2024-07-30	564	--
NVIDIA B300 vs. H200: Is Blackwell Ultra Worth the Upgrade?	Team Vast	2026-06-11	1,100	--
Modular MAX vs vLLM Performance Comparison on Vast.ai	Team Vast	2025-07-29	3,009	--
WAN 2.2 vs. LTX-2: Which AI Video Model Should You Use?	Team Vast	2026-01-26	836	--
February 2024 Product Update	Team Vast	2024-02-28	706	--
January 2025 Product Update	Team Vast	2025-02-05	627	--
Turn Any PDF into an AI-Generated Podcast with Notebook Llama	Team Vast	2024-12-02	920	--
NVIDIA H100 vs. H200: Two Hopper-based Heavyweights	Team Vast	2025-04-28	1,233	--
Navigating Data Center Compliance: Understanding Tier 2/3 and HIPAA/ISO 27001 Standards	Team Vast	2024-01-26	499	--
A Decade Later: Revisiting the Brain as a Universal Learning Machine	Team Vast	2025-06-23	157	--
Running Private AI Models Without the Risk of Data Exposure	Team Vast	2025-10-17	708	--
Serving Online Inference with vLLM API on Vast.ai	Team Vast	2024-04-24	996	--
Build and Test AI Applications with Langflow + Ollama on Vast.ai	Team Vast	2025-09-17	442	--
7 Popular Model Templates for AI Workloads on Vast.ai Right Now	Team Vast	2026-03-22	896	--
Alibaba's Qwen: An Open-Source AI Model that Surpasses DeepSeek?	Team Vast	2025-03-30	640	--
May 2024 Product Update	Team Vast	2024-05-24	460	--
Vast.AI's Model Library: Choosing from the Best AI Models Available	Team Vast	2025-12-23	1,731	--
Everything You Need to Know About the NVIDIA Blackwell Ultra B300	Team Vast	2026-06-03	984	--
Implementing Speech-to-Text with Speaker Diarization: Comparing Pyannote and Sortformer on VAST.ai	Team Vast	2025-03-13	4,208	--
Hybrid AI Inference: Local LiteLLM Proxy with Remote Vast.ai GPU	Team Vast	2025-07-30	1,212	--
Google Colab Explained: Simplifying Your Workflow with Cloud Tools	Team Vast	2026-03-26	872	--
Vast.ai Achieves SOC 2 Type I Certification	Team Vast	2025-04-09	506	--
Absolute Security with NVIDIA Confidential Computing	Team Vast	2024-03-15	908	--
Liquid AI's LFM2 Just Dropped — Here's How to Run It on …	Team Vast	2026-03-05	517	--
Generating Videos with Mochi on Vast.ai	Team Vast	2025-01-23	744	--
Deploy LLMs with dstack on Vast.ai	Team Vast	2026-01-15	327	--
NextEpoch 2024: Bringing Machine Learning to the Next Generation of Scientists	Team Vast	2024-08-15	604	--
NVIDIA RTX 4090 vs. RTX 5090: How They Stack Up	Team Vast	2024-06-21	895	--
Vast Product Update \| April 2024	Team Vast	2024-04-02	738	--
Running Google's Gemma 3 on Vast.ai	Team Vast	2025-04-07	1,191	--
Vast.ai Serverless: Automated GPU Scaling for AI Inference - Without the Overhead	Team Vast	2025-12-08	859	--
NVIDIA H100 vs. L40s: Power Meets Versatility	Team Vast	2024-09-05	1,039	--
How to Build an Agent on Vast.ai in Less Than 100 Lines …	Team Vast	2026-06-12	3,186	--
H100 NVL vs. SXM5: NVIDIA's Supercomputing GPUs	Team Vast	2024-09-10	945	--
Serving Online Inference with Text-Embeddings-Inference on Vast.ai \| June 2024	Team Vast	2024-06-13	546	--
October 2024 Product Update	Team Vast	2024-10-30	445	--
Vast.ai GPUs Can Now Be Rented Through SkyPilot	Team Vast	2026-03-15	1,287	--
DeepSeek R1: Open-Source Disruptor or Overhyped Upstart?	Team Vast	2025-01-30	1,112	--
Model Compression with LLM-Compressor and Deployment on Vast.ai (Part 1)	Team Vast	2025-07-21	2,080	--
Running Nemotron-Cascade-2 on Vast.ai	Team Vast	2026-03-24	529	--
Vast.ai Named Among Fastest Growing Vendors by Ramp and Brex	Team Vast	2026-03-04	535	--
Serving Online Inference with TGI and Medusa on Vast.ai	Team Vast	2024-10-02	1,020	--
August 2024 Product Update from Vast.ai	Team Vast	2024-08-29	744	--
Announcing the Vast.ai Vulnerability Bounty Program	Team Vast	2025-07-23	324	--
February 2025 Product Update	Team Vast	2025-03-05	568	--
Comparing NVIDIA L40 vs. L40s – and More	Team Vast	2024-07-12	1,228	--
Latest AI Model Releases: September and October	Team Vast	2024-10-30	995	--
NVIDIA RTX 5090: Leaks, Rumors, and Next-Gen GPU Performance	Team Vast	2024-07-23	1,021	--
How to Run Karpathy's Autoresearch on Vast H100s	Team Vast	2026-03-30	310	--
Is a Gigawatt Class Data Center Being Built in Kuwait?	Team Vast	2024-02-14	514	--
Announcing Virtual Machine Rental on Vast.ai	Team Vast	2024-12-11	832	--
Deploy Deep Search with DR-Tulu on Vast.ai	Team Vast	2026-01-14	358	--
Voice Activity Detection (VAD) with Pyannote on VAST	Team Vast	2025-03-04	1,382	--
Train a 70b language model on a 2X RTX 3090/4090 with QLoRA …	Team Vast	2024-03-11	749	--
Running ComfyUI on Vast.ai Serverless: Simple, Scalable Image Generation	Team Vast	2025-12-19	678	--
Efficiently Serving Multiple Machine Learning Models with Lorax and vLLM on Vast.ai	Team Vast	2025-06-18	1,236	--
Deploying Qwen-Image for Advanced Text-Integrated Image Generation on Vast.ai	Team Vast	2025-09-02	1,259	--
December 2024 Product Update	Team Vast	2025-01-06	461	--
All-in-One App Studio: Your Complete Creative AI Toolkit in a Single Container	Team Vast	2026-05-13	673	--
Transcribing Audio with Whisper Large V3 on Vast.ai	Team Vast	2025-01-22	1,024	--
Serving Online Inference with LMDeploy on Vast.ai	Team Vast	2024-08-08	562	--
Build a Weather Assistant with OpenAI GPT-OSS and Harmony SDK on Vast.ai	Team Vast	2025-09-06	2,779	--
Speaker Diarization with Pyannote on VAST	Team Vast	2025-04-18	1,678	--
April-May 2025 Product Updates	Team Vast	2025-05-29	929	--
How to Benchmark An LLM with vLLM in 10 Minutes	Team Vast	2025-07-20	999	--
The Future of AI Inference in 2026: Key Trends Shaping AI Infrastructure	Team Vast	2026-06-18	1,038	--
Matryoshka Vector Embeddings: Flexible Embeddings for Cost-Efficient AI Systems	Team Vast	2026-06-26	1,211	--
NVIDIA Rubin Platform: Everything We Know So Far	Team Vast	2026-06-29	749	--
Why AI Agents Cost More Than Chatbots (and How to Architect Around …	Team Vast	2026-07-08	993	--
How Much Does It Cost to Rent a GPU in the Cloud? …	Team Vast	2026-07-22	898	--
Why Vast.ai Is Ideal for Mission-Critical Production Systems	Team Vast	2026-01-28	665	--
Kimi K3: Inside the First 3-Trillion-Class Open-Weight AI Model	Team Vast	2026-07-31	879	--

Plushcap, by Matt Makai. 2021-2026.