feat(catalog): add Gemma 4 12B/QAT entries and RTX 3050 bandwidth (#4728)

Add official Gemma 4 12B-it plus QAT-INT4/INT8 catalog entries (with their
GGUF sources), QAT quantization support across the quant tables and the
prequantized-prefix list, and the missing RTX 3050 / 3050 Ti memory
bandwidth so speed estimates stop falling back to the generic cuda value.
This commit is contained in:
Joel Alejandro Escareño Fernández
2026-06-23 18:23:46 +02:00
committed by GitHub
parent 8f5e36a079
commit 119228a6db
4 changed files with 193 additions and 2 deletions
+1 -1
View File
@@ -9,7 +9,7 @@ from services.hwfit.models import (
GPU_BANDWIDTH = {
"5090": 1792, "5080": 960, "5070 ti": 896, "5070": 672, "5060 ti": 448, "5060": 256,
"4090": 1008, "4080 super": 736, "4080": 717, "4070 ti super": 672, "4070 ti": 504, "4070 super": 504, "4070": 504, "4060 ti": 288, "4060": 272,
"3090 ti": 1008, "3090": 936, "3080 ti": 912, "3080": 760, "3070 ti": 608, "3070": 448, "3060 ti": 448, "3060": 360,
"3090 ti": 1008, "3090": 936, "3080 ti": 912, "3080": 760, "3070 ti": 608, "3070": 448, "3060 ti": 448, "3060": 360, "3050 ti": 192, "3050": 224,
"2080 ti": 616, "2080 super": 496, "2080": 448, "2070 super": 448, "2070": 448, "2060 super": 448, "2060": 336,
"1660 ti": 288, "1660 super": 336, "1660": 192, "1650 super": 192, "1650": 128,
"h100 sxm": 3350, "h100": 2039, "h200": 4800, "a100 sxm": 2039, "a100": 1555,