{"schemaVersion":"hugging-bay.fit-check.v1","generatedAt":"2026-07-10T01:07:22.064Z","artifactId":"hf-model-deepsweet-gigachat3-1-10b-a1-8b-mlx-mxfp8","repo":"deepsweet/GigaChat3.1-10B-A1.8B-MLX-MXFP8","webUrl":"https://huggingbay.xyz/artifact/hf-model-deepsweet-gigachat3-1-10b-a1-8b-mlx-mxfp8","name":"GigaChat3.1-10B-A1.8B-MLX-MXFP8","paramsB":10,"activeB":10,"quant":"f16","weightFile":null,"fileSizeBytes":1,"ctx":8192,"batch":1,"estimate":{"weightsGb":0,"kvGb":1.34,"overheadGb":0.8,"totalGb":2.14},"gpus":[{"id":"t4-16","label":"NVIDIA T4 16GB (free Colab)","vramGb":16,"unified":false,"verdict":"fits","headroomGb":13.86,"totalGb":2.14},{"id":"l4-24","label":"NVIDIA L4 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.86,"totalGb":2.14},{"id":"rtx3060-12","label":"RTX 3060 12GB","vramGb":12,"unified":false,"verdict":"fits","headroomGb":9.86,"totalGb":2.14},{"id":"rtx4080-16","label":"RTX 4080 16GB","vramGb":16,"unified":false,"verdict":"fits","headroomGb":13.86,"totalGb":2.14},{"id":"rtx3090-24","label":"RTX 3090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.86,"totalGb":2.14},{"id":"rtx4090-24","label":"RTX 4090 24GB","vramGb":24,"unified":false,"verdict":"fits","headroomGb":21.86,"totalGb":2.14},{"id":"a100-40","label":"A100 40GB","vramGb":40,"unified":false,"verdict":"fits","headroomGb":37.86,"totalGb":2.14},{"id":"a100-80","label":"A100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":77.86,"totalGb":2.14},{"id":"h100-80","label":"H100 80GB","vramGb":80,"unified":false,"verdict":"fits","headroomGb":77.86,"totalGb":2.14},{"id":"apple-m-16","label":"Apple M-series 16GB (unified)","vramGb":16,"unified":true,"verdict":"fits","headroomGb":13.86,"totalGb":2.14},{"id":"apple-m-32","label":"Apple M-series 32GB (unified)","vramGb":32,"unified":true,"verdict":"fits","headroomGb":29.86,"totalGb":2.14},{"id":"apple-m-64","label":"Apple M-series 64GB (unified)","vramGb":64,"unified":true,"verdict":"fits","headroomGb":61.86,"totalGb":2.14},{"id":"apple-m-128","label":"Apple M-series 128GB (unified)","vramGb":128,"unified":true,"verdict":"fits","headroomGb":125.86,"totalGb":2.14},{"id":"cpu-ram-32","label":"CPU / 32GB system RAM","vramGb":32,"unified":true,"verdict":"fits","headroomGb":29.86,"totalGb":2.14},{"id":"cpu-ram-64","label":"CPU / 64GB system RAM","vramGb":64,"unified":true,"verdict":"fits","headroomGb":61.86,"totalGb":2.14}],"target":{"id":"h100-80","label":"H100 80GB","vramGb":80,"maxCtx":483328},"whatIf":[{"quant":"q2_k","bytesPerParam":0.33,"weightsGb":3.3,"totalGb":5.44,"verdict":"fits","headroomGb":74.56},{"quant":"q3_k_m","bytesPerParam":0.44,"weightsGb":4.4,"totalGb":6.54,"verdict":"fits","headroomGb":73.46},{"quant":"q4_k_m","bytesPerParam":0.57,"weightsGb":5.7,"totalGb":7.84,"verdict":"fits","headroomGb":72.16},{"quant":"q5_k_m","bytesPerParam":0.69,"weightsGb":6.9,"totalGb":9.04,"verdict":"fits","headroomGb":70.96},{"quant":"q6_k","bytesPerParam":0.82,"weightsGb":8.2,"totalGb":10.34,"verdict":"fits","headroomGb":69.66},{"quant":"q8_0","bytesPerParam":1.06,"weightsGb":10.6,"totalGb":12.79,"verdict":"fits","headroomGb":67.21},{"quant":"f16","bytesPerParam":2,"weightsGb":20,"totalGb":22.94,"verdict":"fits","headroomGb":57.06}],"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."]}