NVIDIA-Nemotron-3.5-Lightning-30B-A3B

155 records across 6 hardware.

hardware	model	quant	backend	tok/s	pp tok/s	W	ttft s	ctx/tg	date	class	flags	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	175.5	1465.0	–	–	1024	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	173.1	4315.0	–	–	4096	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	173.1	4315.0	–	–	4096	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	172.9	1800.0	–	–	4096	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	172.9	1800.0	–	–	4096	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	170.5	2458.0	–	–	4096	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	159.7	4080.0	–	–	16384	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	159.7	4080.0	–	–	16384	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	154.9	4106.0	–	–	16384	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	154.9	4106.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	149.4	1613.0	–	–	4096	2026-10-15	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	136.1	2426.0	–	–	1024	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	135.5	1500.0	–	–	16384	2026-10-15	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	135.0	2644.0	–	–	4096	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	134.8	2001.0	–	–	1024	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	134.8	2001.0	–	–	1024	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	134.0	2640.0	–	–	4096	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	134.0	2640.0	–	–	4096	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	133.0	2759.0	–	–	1024	2026-10-08	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	132.4	2591.0	–	–	8192	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	132.1	1883.0	–	–	1024	2026-10-16	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	132.1	1883.0	–	–	1024	2026-10-16	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	131.5	2574.0	–	–	8192	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	131.5	2574.0	–	–	8192	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	131.3	3427.0	–	–	1024	2026-10-07	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	130.9	3619.0	–	–	1024	2026-10-13	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	130.3	1563.0	–	–	1024	2026-10-07	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	129.4	4015.0	–	–	4096	2026-10-07	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	128.6	2469.0	–	–	16384	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	128.6	2469.0	–	–	16384	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	128.4	2073.0	–	–	4096	2026-10-16	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	128.4	2073.0	–	–	4096	2026-10-16	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	127.9	2478.0	–	–	16384	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	126.7	2219.0	–	–	4096	2026-10-07	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	124.4	3352.0	–	–	8192	2026-10-07	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	122.4	2271.0	–	–	32768	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	120.9	1939.0	–	–	16384	2026-10-16	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ4	oMLX	120.9	1939.0	–	–	16384	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	120.8	3351.0	–	–	16384	2026-10-07	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	115.1	3438.0	–	–	32768	2026-10-12	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	114.9	1464.0	–	–	8192	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	114.0	3176.0	–	–	32768	2026-10-07	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	113.6	1273.0	–	–	1024	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	112.9	3607.0	–	–	8192	2026-10-08	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	111.8	1215.0	–	–	1024	2026-10-17	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	110.5	1943.0	–	–	65536	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	109.6	1556.0	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	108.0	1579.0	–	–	4096	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	107.5	1407.0	–	–	8192	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	104.4	874.1	–	–	1024	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	104.2	872.6	–	–	1024	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	104.0	873.5	–	–	1024	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	103.9	866.7	–	–	1024	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	103.8	868.7	–	–	1024	2026-10-15	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	103.3	3253.0	–	–	65536	2026-10-12	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	102.3	2901.0	–	–	65536	2026-10-07	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	101.1	845.9	–	–	1024	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	100.6	818.9	–	–	1024	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	100.6	818.9	–	–	1024	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	100.1	856.5	–	–	1024	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	100.1	856.5	–	–	1024	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	98.5	1153.0	–	–	32768	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	98.2	1333.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	96.7	1441.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	96.7	1441.0	–	–	16384	2026-10-11	community	–	source
M3 Ultra	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	95.8	1506.0	–	–	131072	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	94.2	1459.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	94.2	1459.0	–	–	16384	2026-10-11	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	94.2	626.4	–	–	1024	2026-10-15	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	94.2	626.4	–	–	1024	2026-10-15	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	93.9	1457.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	93.9	1457.0	–	–	16384	2026-10-11	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	93.2	682.3	–	–	4096	2026-10-15	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	93.2	682.3	–	–	4096	2026-10-15	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	92.0	1305.0	–	–	16384	2026-10-17	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	91.7	1452.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	91.7	1452.0	–	–	16384	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	91.5	1172.0	–	–	4096	2026-10-06	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	90.9	1204.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	90.9	1204.0	–	–	32768	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	90.8	2685.0	–	–	131072	2026-10-12	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	90.4	1293.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	90.4	1293.0	–	–	32768	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	90.0	802.0	–	–	4096	2026-10-15	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	89.9	1160.0	–	–	32768	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	89.4	804.0	–	–	4096	2026-10-15	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	88.9	2597.0	–	–	131072	2026-10-10	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	88.9	1246.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	88.9	1246.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	88.1	1254.0	–	–	32768	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	88.1	1254.0	–	–	32768	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	87.9	794.3	–	–	4096	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	87.2	800.3	–	–	4096	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	87.0	786.4	–	–	4096	2026-10-15	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	86.5	677.1	–	–	8192	2026-10-15	community	–	source
M4 Pro	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	86.5	677.1	–	–	8192	2026-10-15	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	86.4	782.2	–	–	4096	2026-10-15	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	85.6	2370.0	–	–	131072	2026-10-07	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	85.3	825.1	–	–	4096	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	85.3	825.1	–	–	4096	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	82.7	784.7	–	–	4096	2026-10-11	community	–	source
M2 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	82.7	784.7	–	–	4096	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	77.9	969.2	–	–	65536	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	77.7	2219.0	–	–	199680	2026-10-10	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	77.4	977.1	–	–	65536	2026-10-11	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ6	oMLX	72.3	2197.0	–	–	199680	2026-10-08	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	OptiQ-4bit	oMLX	71.6	1927.0	–	–	199680	2026-10-07	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.9	2031.0	–	–	4096	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.8	1134.0	–	–	1024	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.6	2160.0	–	–	1024	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.6	2081.0	–	–	1024	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.3	2948.0	–	–	4096	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.2	2899.0	–	–	4096	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.1	2831.0	–	–	8192	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	67.0	2813.0	–	–	16384	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	66.2	2703.0	–	–	32768	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	65.5	2828.0	–	–	4096	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	63.3	2439.0	–	–	65536	2026-10-16	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	63.1	617.0	–	–	131072	2026-10-17	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	62.9	1994.0	–	–	1024	2026-10-16	community	–	source
M1 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	8bit	oMLX	60.8	474.7	–	–	1024	2026-10-15	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	58.4	2033.0	–	–	131072	2026-10-16	community	–	source
M5 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	bf16	oMLX	53.8	1797.0	–	–	199680	2026-10-16	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	4bit	oMLX	50.6	607.4	–	–	199680	2026-10-13	community	–	source
M4 Max	NVIDIA-Nemotron-3.5-Lightning-30B-A3B	oQ8e	oMLX	41.5	432.3	–	–	199680	2026-10-17	community	–	source

← all models