https://nodegrove.io/ What Nodegrove measured on rented GPUs, and the data sheets, tools and guides whose numbers changed, newest first. en Tue, 03 Nov 2026 00:00:00 GMT https://nodegrove.io/create tag:nodegrove.io,2026-11-03:/create Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM open image and video models need in ComfyUI, worked out from the exact files. https://nodegrove.io/data tag:nodegrove.io,2026-11-03:/data Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Memory for every open model on the site at each quantisation and common context length, and which GPUs run each one, as CSV and JSON under CC BY 4.0. https://nodegrove.io/gpus tag:nodegrove.io,2026-11-03:/gpus Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Every card against the same open models: the pick at each memory size, what fits at Q4 and how fast each answers. https://nodegrove.io/models tag:nodegrove.io,2026-11-03:/models Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Every open model measured the same way: memory at Q4 and Q8, what each 1,000 tokens of context costs, and the smallest GPU that runs each one. https://nodegrove.io/where-to-run tag:nodegrove.io,2026-11-03:/where-to-run Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Your own GPU, Comfy Cloud, a cloud GPU by the hour or a per-clip API: what each costs, and when each one wins. https://nodegrove.io/tools/ai-computer-picker tag:nodegrove.io,2026-11-03:/tools/ai-computer-picker Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. What to get to run AI yourself: every machine checked against your job, and what renting it costs instead. https://nodegrove.io/tools/can-i-run-it tag:nodegrove.io,2026-11-03:/tools/can-i-run-it Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Your card, any model: fits or not, how fast, and what to change when it does not. https://nodegrove.io/tools/comfyui-vram-checker tag:nodegrove.io,2026-11-03:/tools/comfyui-vram-checker Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Any open image or video model on your card: which file to download, stage by stage. https://nodegrove.io/tools/comfyui-workflow-checker tag:nodegrove.io,2026-11-03:/tools/comfyui-workflow-checker Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Drop a workflow: every model file it loads, the VRAM it needs, what to swap and the custom nodes. https://nodegrove.io/tools/llm-speed-estimator tag:nodegrove.io,2026-11-03:/tools/llm-speed-estimator Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How fast a model runs on a given GPU, from bandwidth and weight size. https://nodegrove.io/tools/llm-vram-calculator tag:nodegrove.io,2026-11-03:/tools/llm-vram-calculator Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Weights + KV cache + overhead for any model, with the formula shown. https://nodegrove.io/guides/cloud-gpu tag:nodegrove.io,2026-11-03:/guides/cloud-gpu Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. On-demand prices from 13 providers for every card from the RTX 4090 to the B200, the card your model needs, the price per token, and what the hourly rate leaves out. https://nodegrove.io/guides/comfyui-api tag:nodegrove.io,2026-11-03:/guides/comfyui-api Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Comfy API, RunComfy, ViewComfy, fal, Replicate, RunPod Serverless and Modal: what a GPU hour and one job cost, custom nodes, cold starts, agent spend limits and privacy. https://nodegrove.io/guides/comfyui-cloud tag:nodegrove.io,2026-11-03:/guides/comfyui-cloud Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Comfy Cloud, RunComfy, ThinkDiffusion, MimicPC, Floyo, RunPod and Vast.ai: price per hour by card, what idle time costs, nodes, files and privacy. https://nodegrove.io/guides/dgx-spark-vs-strix-halo-vs-mac-studio tag:nodegrove.io,2026-11-03:/guides/dgx-spark-vs-strix-halo-vs-mac-studio Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. The three big-memory boxes for local LLMs: memory the GPU can use, bandwidth, software, and speed on the same models. https://nodegrove.io/guides/ollama-cloud tag:nodegrove.io,2026-11-03:/guides/ollama-cloud Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. What a month of credits buys on each cloud model, which ones fit a machine at home, and what Ollama says about your prompts. https://nodegrove.io/guides/openclaw-vram-requirements tag:nodegrove.io,2026-11-03:/guides/openclaw-vram-requirements Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. The context OpenClaw asks for, what it costs in memory, and the best tool-calling model for 12, 16 and 24 GB. https://nodegrove.io/guides/personal-ai-computer tag:nodegrove.io,2026-11-03:/guides/personal-ai-computer Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Ghost Core, DGX Spark, Strix Halo, Mac mini, Mac Studio and RTX PCs: the memory each GPU can use, its speed, and the models each one runs, agents included. https://nodegrove.io/guides/private-ai-server tag:nodegrove.io,2026-11-03:/guides/private-ai-server Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. What "private" means at each layer, and the three ways to get one, honestly compared. https://nodegrove.io/guides/self-hosted-llm tag:nodegrove.io,2026-11-03:/guides/self-hosted-llm Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How VRAM is really used, the runtimes that matter, quantisation without the mysticism, and a calculator. https://nodegrove.io/guides/what-fits-on-24-48-96-gb tag:nodegrove.io,2026-11-03:/guides/what-fits-on-24-48-96-gb Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. Estimated VRAM for popular open models at Q4 and Q8, 8k and 32k context, with the smallest card that fits. https://nodegrove.io/private-ai-for-business tag:nodegrove.io,2026-11-03:/private-ai-for-business Tue, 03 Nov 2026 00:00:00 GMT Published 3 November 2026. What one machine in your office runs for a team, sized by how many people ask at once, what renting instead costs, and a setup proposal on request. https://nodegrove.io/create/anima tag:nodegrove.io,2026-11-03:/create/anima Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM Anima needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/fasth3 tag:nodegrove.io,2026-11-03:/create/fasth3 Tue, 03 Nov 2026 00:00:00 GMT Published 3 November 2026. How much VRAM FastH3 needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/fibo-2.0 tag:nodegrove.io,2026-11-03:/create/fibo-2.0 Tue, 03 Nov 2026 00:00:00 GMT Published 3 November 2026. How much VRAM Fibo 2.0 needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/flux-2 tag:nodegrove.io,2026-11-03:/create/flux-2 Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM FLUX.2 needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/flux-3-image-klein tag:nodegrove.io,2026-11-03:/create/flux-3-image-klein Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM FLUX 3 Image Klein needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/hunyuanvideo-1.5 tag:nodegrove.io,2026-11-03:/create/hunyuanvideo-1.5 Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM HunyuanVideo 1.5 needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/create/krea-2 tag:nodegrove.io,2026-11-03:/create/krea-2 Tue, 03 Nov 2026 00:00:00 GMT Updated 3 November 2026. How much VRAM Krea 2 needs in ComfyUI, which file fits each card size, and where to run it. https://nodegrove.io/benchmarks tag:nodegrove.io,2026-10-20:/benchmarks#finding Tue, 20 Oct 2026 00:00:00 GMT In Nodegrove's runs of 20 October 2026, an RTX PRO 6000 finished three AI jobs 2.7 to 3.5 times faster than an RTX 6000 Ada and cost 35 to 50% less per output, at on-demand list prices. For LLMs, our memory estimate came within 1% of the peak we measured.