{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-10T01:10:51.512Z","artifactId":"hf-model-mradermacher-arkoda-70b-v2-merged-i1-gguf","repo":"mradermacher/arkoda-70b-v2-merged-i1-GGUF","webUrl":"https://huggingbay.xyz/artifact/hf-model-mradermacher-arkoda-70b-v2-merged-i1-gguf","name":"arkoda-70b-v2-merged-i1-GGUF","paramsB":70,"activeB":70,"quant":"f16","weightFile":"arkoda-70b-v2-merged.i1-IQ1_M.gguf","fileSizeBytes":1,"ctx":8192,"batch":1,"estimate":{"weightsGb":0,"kvGb":2.68,"overheadGb":0.8,"totalGb":3.48},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"fits","headroomGb":12.52,"totalGb":3.48},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":20.52,"totalGb":3.48},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"fits","headroomGb":8.52,"totalGb":3.48},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"fits","headroomGb":12.52,"totalGb":3.48},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":20.52,"totalGb":3.48},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":20.52,"totalGb":3.48},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"fits","headroomGb":36.52,"totalGb":3.48},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":76.52,"totalGb":3.48},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":76.52,"totalGb":3.48},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"fits","headroomGb":12.52,"totalGb":3.48},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"fits","headroomGb":28.52,"totalGb":3.48},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"fits","headroomGb":60.52,"totalGb":3.48},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"fits","headroomGb":124.52,"totalGb":3.48},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"fits","headroomGb":28.52,"totalGb":3.48},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"fits","headroomGb":60.52,"totalGb":3.48}],"target":{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"maxCtx":70656},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":23.1,"totalGb":27.63,"verdict":"no","headroomGb":-3.63},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":30.8,"totalGb":35.95,"verdict":"no","headroomGb":-11.95},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":39.9,"totalGb":45.78,"verdict":"no","headroomGb":-21.78},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":48.3,"totalGb":54.85,"verdict":"no","headroomGb":-30.85},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":57.4,"totalGb":64.68,"verdict":"no","headroomGb":-40.68},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":74.2,"totalGb":82.82,"verdict":"no","headroomGb":-58.82},{"quant":"f16","bytesPerParam":2,"weightsGb":140,"totalGb":153.88,"verdict":"no","headroomGb":-129.88}],"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."]}