{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-11T04:40:35.414Z","artifactId":"hf-model-mradermacher-nous-hermes-2-yi-34b-i1-gguf","repo":"mradermacher/Nous-Hermes-2-Yi-34B-i1-GGUF","webUrl":"https://huggingbay.xyz/artifact/hf-model-mradermacher-nous-hermes-2-yi-34b-i1-gguf","name":"Nous-Hermes-2-Yi-34B-i1-GGUF","paramsB":34,"activeB":34,"quant":"f16","weightFile":"Nous-Hermes-2-Yi-34B.i1-IQ1_M.gguf","fileSizeBytes":null,"ctx":8192,"batch":1,"estimate":{"weightsGb":68,"kvGb":1.61,"overheadGb":5.44,"totalGb":75.05},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"no","headroomGb":-59.05,"totalGb":75.05},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-51.05,"totalGb":75.05},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"no","headroomGb":-63.05,"totalGb":75.05},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"no","headroomGb":-59.05,"totalGb":75.05},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-51.05,"totalGb":75.05},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"no","headroomGb":-51.05,"totalGb":75.05},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"no","headroomGb":-35.05,"totalGb":75.05},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"tight","headroomGb":4.95,"totalGb":75.05},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"tight","headroomGb":4.95,"totalGb":75.05},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"no","headroomGb":-59.05,"totalGb":75.05},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"no","headroomGb":-43.05,"totalGb":75.05},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"no","headroomGb":-11.05,"totalGb":75.05},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"fits","headroomGb":52.95,"totalGb":75.05},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"no","headroomGb":-43.05,"totalGb":75.05},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"no","headroomGb":-11.05,"totalGb":75.05}],"target":{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"maxCtx":0},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":11.22,"totalGb":13.73,"verdict":"no","headroomGb":-1.73},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":14.96,"totalGb":17.77,"verdict":"no","headroomGb":-5.77},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":19.38,"totalGb":22.54,"verdict":"no","headroomGb":-10.54},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":23.46,"totalGb":26.95,"verdict":"no","headroomGb":-14.95},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":27.88,"totalGb":31.72,"verdict":"no","headroomGb":-19.72},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":36.04,"totalGb":40.53,"verdict":"no","headroomGb":-28.53},{"quant":"f16","bytesPerParam":2,"weightsGb":68,"totalGb":75.05,"verdict":"no","headroomGb":-63.05}],"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."]}