Hugging Face released gr.Workflow, a feature built into Gradio that turns AI pipelines into interactive drag-and-drop canvases where each node is runnable and every intermediate result is visible, whi…
Hugging Face user dayona reported difficulties securing ZeroGPU allocations, frequently encountering timeouts or no GPU available, and asked whether others face the same issue or if there is an ongoin…
Hugging Face user dayona reported that a newly created Space using ZeroGPU crashes and restarts immediately after initialization, with the error log showing 'ZeroGPU tensors packing: 100%|██████████| …
Hugging Face user AbstractPhil reports that their ZeroGPU Space 'AbstractPhil/alephllm-chat' builds successfully but never receives a hardware allocation, with the runtime API showing 'hardware.curren…
A Hugging Face agents course user encountered a runtime error when duplicating the first agent example on ZeroGPU, with the message 'No @spaces.GPU function detected during startup.' The fix involves …
Hugging Face's free ZeroGPU quota is 5 GPU-minutes per day per account, but a separate request-based limit of 3 runs per day for free users was confirmed by Hugging Face staff member hysts in an April…
HuggingChat's Omni model can generate images directly through a built-in tool, with a practical limit of about 3 images per day for free accounts, according to public information and a Hugging Face de…
Hugging Face clarifies that Hugging Chat's free tier is powered by Inference Providers, not ZeroGPU, meaning users exhaust a monthly inference credit allowance that resets on the first of each month, …
Hugging Face users who see a 'You have exceeded your Pro GPU quota' error despite having loaded credits are likely misunderstanding the platform's separate billing systems, according to Hugging Face d…
A user reports a ZeroGPU connection issue via the Anthropic MCP connector, with the error 'Anthropic proxy: MCP server connection lost' and 'Model not loaded'. An open GitHub issue (anthropics/claude-…
An independent open-source developer has filed an official community complaint against Hugging Face, demanding the reversion of recent free-tier changes that eliminated CPU Basic instances, restricted…
Hugging Face's ZeroGPU shared GPU infrastructure consumes quota based on reservation time, not successful output, meaning failed generation attempts still deduct from the user's quota. The system book…
Hugging Face appears to have restricted free accounts from creating CPU Basic Gradio Spaces, leaving only ZeroGPU as the available runtime. Users report that Docker is marked as paid and switching to …
AI company ZeroGPU launched specialized small language models for ad tech on Thursday, aiming to help companies handle high-volume workflows faster and at lower cost. The SLMs, which run on cheaper CP…
A developer built a Claude Code plugin that routes lightweight AI tasks to specialized small language models (SLMs) to reduce compute costs. The plugin intercepts requests and directs simpler queries …
ZeroGPU released a Batch API that enables overnight tagging of customer reviews using a small, efficient model (LFM2.5-1.2B-Instruct) instead of expensive frontier LLMs. The API processes thousands of…
A team of developers has built an AI-powered job search tool that uses a fine-tuned Qwen3-8B language model to generate LinkedIn queries, scrape job postings, and score each role against a candidate's…
ZeroGPU has launched a Batch Processing API for asynchronous AI workloads, allowing developers to upload JSONL files for batch jobs and retrieve results upon completion. The new feature supports large…