{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-11T04:59:32.894Z","artifactId":"hf-model-disty0-qwen3-vl-8b-nsfw-caption-v4-5","repo":"Disty0/Qwen3-VL-8B-NSFW-Caption-V4.5","webUrl":"https://huggingbay.xyz/artifact/hf-model-disty0-qwen3-vl-8b-nsfw-caption-v4-5","name":"Qwen3-VL-8B-NSFW-Caption-V4.5","paramsB":8,"activeB":8,"quant":"f16","weightFile":null,"fileSizeBytes":null,"ctx":8192,"batch":1,"estimate":{"weightsGb":16,"kvGb":1.07,"overheadGb":1.28,"totalGb":18.35},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"no","headroomGb":-2.35,"totalGb":18.35},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":5.65,"totalGb":18.35},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"no","headroomGb":-6.35,"totalGb":18.35},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"no","headroomGb":-2.35,"totalGb":18.35},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":5.65,"totalGb":18.35},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":5.65,"totalGb":18.35},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"fits","headroomGb":21.65,"totalGb":18.35},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":61.65,"totalGb":18.35},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":61.65,"totalGb":18.35},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"no","headroomGb":-2.35,"totalGb":18.35},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"fits","headroomGb":13.65,"totalGb":18.35},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"fits","headroomGb":45.65,"totalGb":18.35},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"fits","headroomGb":109.65,"totalGb":18.35},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"fits","headroomGb":13.65,"totalGb":18.35},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"fits","headroomGb":45.65,"totalGb":18.35}],"target":{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"maxCtx":0},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":2.64,"totalGb":4.51,"verdict":"fits","headroomGb":7.49},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":3.52,"totalGb":5.39,"verdict":"fits","headroomGb":6.61},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":4.56,"totalGb":6.43,"verdict":"fits","headroomGb":5.57},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":5.52,"totalGb":7.39,"verdict":"fits","headroomGb":4.61},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":6.56,"totalGb":8.43,"verdict":"fits","headroomGb":3.57},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":8.48,"totalGb":10.35,"verdict":"fits","headroomGb":1.65},{"quant":"f16","bytesPerParam":2,"weightsGb":16,"totalGb":18.35,"verdict":"no","headroomGb":-6.35}],"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."]}