{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-10T03:18:05.753Z","artifactId":"modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4","repo":"unsloth/nvidia-nemotron-3-ultra-550b-a55b-nvfp4","webUrl":"https://huggingbay.xyz/artifact/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4","name":"nvidia-nemotron-3-ultra-550b-a55b-nvfp4","paramsB":550,"activeB":550,"quant":"f16","weightFile":null,"fileSizeBytes":352385960457,"ctx":8192,"batch":1,"estimate":{"weightsGb":352.39,"kvGb":3.22,"overheadGb":28.19,"totalGb":383.8},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"no","headroomGb":-367.8,"totalGb":383.8},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-359.8,"totalGb":383.8},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"no","headroomGb":-371.8,"totalGb":383.8},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"no","headroomGb":-367.8,"totalGb":383.8},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-359.8,"totalGb":383.8},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-359.8,"totalGb":383.8},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"no","headroomGb":-343.8,"totalGb":383.8},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"no","headroomGb":-303.8,"totalGb":383.8},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"no","headroomGb":-303.8,"totalGb":383.8},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"no","headroomGb":-367.8,"totalGb":383.8},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"no","headroomGb":-351.8,"totalGb":383.8},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"no","headroomGb":-319.8,"totalGb":383.8},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"no","headroomGb":-255.8,"totalGb":383.8},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"no","headroomGb":-351.8,"totalGb":383.8},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"no","headroomGb":-319.8,"totalGb":383.8}],"target":{"id":"a100-80","label":"A100 80GB","vramGb":80,"maxCtx":0},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":181.5,"totalGb":199.24,"verdict":"no","headroomGb":-119.24},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":242,"totalGb":264.58,"verdict":"no","headroomGb":-184.58},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":313.5,"totalGb":341.8,"verdict":"no","headroomGb":-261.8},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":379.5,"totalGb":413.08,"verdict":"no","headroomGb":-333.08},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":451,"totalGb":490.3,"verdict":"no","headroomGb":-410.3},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":583,"totalGb":632.86,"verdict":"no","headroomGb":-552.86},{"quant":"f16","bytesPerParam":2,"weightsGb":1100,"totalGb":1191.22,"verdict":"no","headroomGb":-1111.22}],"guidance":["verdict per GPU: fits (<=90% VRAM) / tight (<=100%) / no.","If it does not fit at this precision, check /api/artifacts/{id}/quantizations or the per-quant rows for a smaller mirror.","Estimates: weights + fp16 KV-cache(ctx,batch) + overhead. Real usage varies by runtime."]}