{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-10T01:04:40.877Z","artifactId":"hf-model-mradermacher-mistral-small-24b-instruct-2501-gguf","repo":"mradermacher/Mistral-Small-24B-Instruct-2501-GGUF","webUrl":"https://huggingbay.xyz/artifact/hf-model-mradermacher-mistral-small-24b-instruct-2501-gguf","name":"Mistral-Small-24B-Instruct-2501-GGUF","paramsB":24,"activeB":24,"quant":"q4_k_s","weightFile":"Mistral-Small-24B-Instruct-2501.IQ4_XS.gguf","fileSizeBytes":1,"ctx":8192,"batch":1,"estimate":{"weightsGb":0,"kvGb":1.61,"overheadGb":0.8,"totalGb":2.41},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"fits","headroomGb":13.59,"totalGb":2.41},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.59,"totalGb":2.41},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"fits","headroomGb":9.59,"totalGb":2.41},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"fits","headroomGb":13.59,"totalGb":2.41},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.59,"totalGb":2.41},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.59,"totalGb":2.41},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"fits","headroomGb":37.59,"totalGb":2.41},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":77.59,"totalGb":2.41},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":77.59,"totalGb":2.41},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"fits","headroomGb":13.59,"totalGb":2.41},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"fits","headroomGb":29.59,"totalGb":2.41},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"fits","headroomGb":61.59,"totalGb":2.41},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"fits","headroomGb":125.59,"totalGb":2.41},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"fits","headroomGb":29.59,"totalGb":2.41},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"fits","headroomGb":61.59,"totalGb":2.41}],"target":{"id":"h100-80","label":"H100 80GB","vramGb":80,"maxCtx":402688},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":7.92,"totalGb":10.33,"verdict":"fits","headroomGb":69.67},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":10.56,"totalGb":13.02,"verdict":"fits","headroomGb":66.98},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":13.68,"totalGb":16.39,"verdict":"fits","headroomGb":63.61},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":16.56,"totalGb":19.5,"verdict":"fits","headroomGb":60.5},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":19.68,"totalGb":22.87,"verdict":"fits","headroomGb":57.13},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":25.44,"totalGb":29.09,"verdict":"fits","headroomGb":50.91},{"quant":"f16","bytesPerParam":2,"weightsGb":48,"totalGb":53.45,"verdict":"fits","headroomGb":26.55}],"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."]}