MiniMax M2.7

Current smaller MiniMax for coding, reasoning and office tasks.

Stored parameters 228.7B

Native context 200Ktokens

ArchitectureMixture of experts

Memory by precision and context

GiB · one request · FP16 cache · default single-device buffers. Extended contexts are marked *. Text inference only.

Weight precision	Weights	8K total	32K total	128K total	200K total
Q4 · smaller	127.8	140.0	145.8	169.0	186.5
Q5 · medium	151.8	165.8	171.6	194.9	212.3
Q8 · larger	226.3	246.3	252.1	275.4	292.8
FP16 / BF16	426.0	462.0	467.8	491.0	508.5

Hardware fit at Q4 and 8K

One request, FP16 cache. Multi-GPU and compressed or sliding caches require compatible runtime support.

View 199 hardware configurations

Hardware	Memory needed	Available	Estimate
GeForce RTX 50508 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 50608 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 5060 Ti 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 5060 Ti 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 507012 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 5070 Ti16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 508016 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 509032 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
GeForce RTX 3060 12 GB12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 4060 Ti 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 4070 Ti SUPER16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 309024 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
GeForce RTX 3090 Ti24 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
GeForce RTX 409024 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
GeForce RTX 40608 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 4060 Ti 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 4070 GDDR6X12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 4070 SUPER12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 4070 Ti12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 408016 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 4080 SUPER16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 5090 Laptop GPU 24 GB24 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
GeForce RTX 5080 Laptop GPU 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 5070 Ti Laptop GPU 12 GB12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 5070 Laptop GPU 12 GB12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 5070 Laptop GPU 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 5060 Laptop GPU 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 5050 Laptop GPU 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 4090 Laptop GPU 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
GeForce RTX 4080 Laptop GPU 12 GB12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 4070 Laptop GPU 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 4060 Laptop GPU 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 4050 Laptop GPU 6 GB6 GiB · GPU	140.0 GiB	5.0 GiB	Over capacity
RTX PRO 2000 Blackwell16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
RTX PRO 4000 Blackwell SFF24 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
RTX PRO 4000 Blackwell24 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
RTX PRO 4500 Blackwell Workstation32 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
RTX PRO 5000 Blackwell 48 GB48 GiB · GPU	140.0 GiB	47.0 GiB	Over capacity
RTX PRO 5000 Blackwell 72 GB72 GiB · GPU	140.0 GiB	71.0 GiB	Over capacity
RTX PRO 6000 Blackwell Workstation96 GiB · GPU	140.0 GiB	95.0 GiB	Over capacity
RTX PRO 6000 Blackwell Max-Q96 GiB · GPU	140.0 GiB	95.0 GiB	Over capacity
RTX A600048 GiB · GPU	140.0 GiB	47.0 GiB	Over capacity
RTX 6000 Ada Generation48 GiB · GPU	140.0 GiB	47.0 GiB	Over capacity
RTX 5000 Ada Generation32 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
A100 80 GB PCIe80 GiB · GPU	140.0 GiB	78.0 GiB	Over capacity
A100 80 GB SXM80 GiB · GPU	140.0 GiB	78.0 GiB	Over capacity
H100 80 GB SXM80 GiB · GPU	140.0 GiB	78.0 GiB	Over capacity
H100 NVL 94 GB PCIe94 GiB · GPU	140.0 GiB	92.0 GiB	Over capacity
H200 141 GB SXM141 GiB · GPU	140.0 GiB	139.0 GiB	Over capacity
H200 NVL 141 GB PCIe141 GiB · GPU	140.0 GiB	139.0 GiB	Over capacity
L40S48 GiB · GPU	140.0 GiB	46.0 GiB	Over capacity
B200 180 GB SXM180 GiB · GPU	140.0 GiB	178.0 GiB	Room to spare
B300 288 GB SXM288 GiB · GPU	140.0 GiB	286.0 GiB	Room to spare
A4048 GiB · GPU	140.0 GiB	46.0 GiB	Over capacity
Radeon RX 680016 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 6800 XT16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 6950 XT16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 7600 XT16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 7700 XT12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Radeon RX 7800 XT16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 7900 GRE16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 7900 XT20 GiB · GPU	140.0 GiB	19.0 GiB	Over capacity
Radeon RX 7900 XTX24 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
Radeon RX 9060 XT 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 9070 GRE12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Radeon RX 907016 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon RX 9070 XT16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Radeon AI PRO R970032 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
Radeon PRO W7800 32 GB32 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
Radeon PRO W7800 48 GB48 GiB · GPU	140.0 GiB	47.0 GiB	Over capacity
Radeon PRO W790048 GiB · GPU	140.0 GiB	47.0 GiB	Over capacity
Instinct MI210 PCIe64 GiB · GPU	140.0 GiB	62.0 GiB	Over capacity
Instinct MI300X OAM192 GiB · GPU	140.0 GiB	190.0 GiB	Room to spare
Instinct MI325X OAM256 GiB · GPU	140.0 GiB	254.0 GiB	Room to spare
Instinct MI350X OAM288 GiB · GPU	140.0 GiB	286.0 GiB	Room to spare
Instinct MI355X OAM288 GiB · GPU	140.0 GiB	286.0 GiB	Room to spare
Instinct MI350P PCIe144 GiB · GPU	140.0 GiB	142.0 GiB	Tight fit
Arc Pro B5016 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Arc Pro B6024 GiB · GPU	140.0 GiB	23.0 GiB	Over capacity
Arc Pro B6532 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
Arc Pro B7032 GiB · GPU	140.0 GiB	31.0 GiB	Over capacity
Arc A770 16 GB16 GiB · GPU	140.0 GiB	15.0 GiB	Over capacity
Arc B57010 GiB · GPU	140.0 GiB	9.0 GiB	Over capacity
Arc B58012 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Mac mini M1 · 8 GB (8-core GPU)8 GiB · Unified memory	140.0 GiB	6.0 GiB	Over capacity
Mac mini M1 · 16 GB (8-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
Mac mini M2 · 8 GB (10-core GPU)8 GiB · Unified memory	140.0 GiB	6.0 GiB	Over capacity
Mac mini M2 · 16 GB (10-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
Mac mini M2 · 24 GB (10-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
Mac mini M2 Pro · 16 GB (16-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
Mac mini M2 Pro · 32 GB (16-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac mini M2 Pro · 16 GB (19-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
Mac mini M2 Pro · 32 GB (19-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
MacBook Air M3 · 8 GB (8-core GPU)8 GiB · Unified memory	140.0 GiB	6.0 GiB	Over capacity
MacBook Air M3 · 16 GB (8-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
MacBook Air M3 · 24 GB (8-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
MacBook Air M3 · 8 GB (10-core GPU)8 GiB · Unified memory	140.0 GiB	6.0 GiB	Over capacity
MacBook Air M3 · 16 GB (10-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
MacBook Air M3 · 24 GB (10-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
MacBook Pro M1 Pro · 16 GB (16-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
MacBook Pro M1 Pro · 32 GB (16-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac Studio M1 Max · 32 GB (24-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac Studio M1 Max · 64 GB (24-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M1 Max · 32 GB (32-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac Studio M1 Max · 64 GB (32-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M1 Ultra · 64 GB (48-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M1 Ultra · 128 GB (48-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac Studio M1 Ultra · 64 GB (64-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M1 Ultra · 128 GB (64-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac Studio M2 Max · 32 GB (30-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac Studio M2 Max · 64 GB (30-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M2 Max · 32 GB (38-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac Studio M2 Max · 64 GB (38-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M2 Max · 96 GB (38-core GPU)96 GiB · Unified memory	140.0 GiB	72.0 GiB	Over capacity
Mac Studio M2 Ultra · 64 GB (60-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M2 Ultra · 128 GB (60-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac Studio M2 Ultra · 192 GB (60-core GPU)192 GiB · Unified memory	140.0 GiB	144.0 GiB	Tight fit
Mac Studio M2 Ultra · 64 GB (76-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M2 Ultra · 128 GB (76-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac Studio M2 Ultra · 192 GB (76-core GPU)192 GiB · Unified memory	140.0 GiB	144.0 GiB	Tight fit
MacBook Pro M3 Pro · 18 GB (18-core GPU)18 GiB · Unified memory	140.0 GiB	13.5 GiB	Over capacity
MacBook Pro M3 Pro · 36 GB (18-core GPU)36 GiB · Unified memory	140.0 GiB	27.0 GiB	Over capacity
MacBook Pro M3 Max · 36 GB (30-core GPU)36 GiB · Unified memory	140.0 GiB	27.0 GiB	Over capacity
MacBook Pro M3 Max · 96 GB (30-core GPU)96 GiB · Unified memory	140.0 GiB	72.0 GiB	Over capacity
MacBook Pro M3 Max · 48 GB (40-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
MacBook Pro M3 Max · 64 GB (40-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
MacBook Pro M3 Max · 128 GB (40-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac mini M4 · 16 GB (10-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
Mac mini M4 · 24 GB (10-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
Mac mini M4 · 32 GB (10-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Mac mini M4 Pro · 24 GB (16-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
Mac mini M4 Pro · 48 GB (16-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
Mac mini M4 Pro · 64 GB (16-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac mini M4 Pro · 24 GB (20-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
Mac mini M4 Pro · 48 GB (20-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
Mac mini M4 Pro · 64 GB (20-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M4 Max · 36 GB (32-core GPU)36 GiB · Unified memory	140.0 GiB	27.0 GiB	Over capacity
Mac Studio M4 Max · 48 GB (40-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
Mac Studio M4 Max · 64 GB (40-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Mac Studio M4 Max · 128 GB (40-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Mac Studio M3 Ultra · 96 GB (60-core GPU)96 GiB · Unified memory	140.0 GiB	72.0 GiB	Over capacity
Mac Studio M3 Ultra · 256 GB (60-core GPU)256 GiB · Unified memory	140.0 GiB	192.0 GiB	Room to spare
Mac Studio M3 Ultra · 96 GB (80-core GPU)96 GiB · Unified memory	140.0 GiB	72.0 GiB	Over capacity
Mac Studio M3 Ultra · 256 GB (80-core GPU)256 GiB · Unified memory	140.0 GiB	192.0 GiB	Room to spare
Mac Studio M3 Ultra · 512 GB (80-core GPU)512 GiB · Unified memory	140.0 GiB	384.0 GiB	Room to spare
MacBook Pro M5 · 16 GB (10-core GPU)16 GiB · Unified memory	140.0 GiB	12.0 GiB	Over capacity
MacBook Pro M5 · 24 GB (10-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
MacBook Pro M5 · 32 GB (10-core GPU)32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
MacBook Pro M5 Pro · 24 GB (16-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
MacBook Pro M5 Pro · 48 GB (16-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
MacBook Pro M5 Pro · 24 GB (20-core GPU)24 GiB · Unified memory	140.0 GiB	18.0 GiB	Over capacity
MacBook Pro M5 Pro · 48 GB (20-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
MacBook Pro M5 Pro · 64 GB (20-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
MacBook Pro M5 Max · 36 GB (32-core GPU)36 GiB · Unified memory	140.0 GiB	27.0 GiB	Over capacity
MacBook Pro M5 Max · 48 GB (40-core GPU)48 GiB · Unified memory	140.0 GiB	36.0 GiB	Over capacity
MacBook Pro M5 Max · 64 GB (40-core GPU)64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
MacBook Pro M5 Max · 128 GB (40-core GPU)128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Ryzen AI Max+ 395 · 32 GB32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Ryzen AI Max+ 395 · 64 GB64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Ryzen AI Max+ 395 · 128 GB128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Ryzen AI Max+ 392 · 32 GB32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Ryzen AI Max+ 392 · 64 GB64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Ryzen AI Max+ 392 · 128 GB128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
Ryzen AI Max+ 388 · 32 GB32 GiB · Unified memory	140.0 GiB	24.0 GiB	Over capacity
Ryzen AI Max+ 388 · 64 GB64 GiB · Unified memory	140.0 GiB	48.0 GiB	Over capacity
Ryzen AI Max+ 388 · 128 GB128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
NVIDIA DGX Spark · 128 GB128 GiB · Unified memory	140.0 GiB	96.0 GiB	Over capacity
2 × GeForce RTX 309048 GiB · Multi-GPU	140.0 GiB	46.0 GiB	Conditional · Over capacity
4 × GeForce RTX 309096 GiB · Multi-GPU	140.0 GiB	92.0 GiB	Conditional · Over capacity
2 × GeForce RTX 409048 GiB · Multi-GPU	140.0 GiB	46.0 GiB	Conditional · Over capacity
2 × GeForce RTX 509064 GiB · Multi-GPU	140.0 GiB	62.0 GiB	Conditional · Over capacity
4 × GeForce RTX 5090128 GiB · Multi-GPU	140.0 GiB	124.0 GiB	Conditional · Over capacity
2 × GeForce RTX 5060 Ti 16 GB32 GiB · Multi-GPU	140.0 GiB	30.0 GiB	Conditional · Over capacity
2 × RTX A600096 GiB · Multi-GPU	140.0 GiB	94.0 GiB	Conditional · Over capacity
2 × RTX PRO 5000 Blackwell 72 GB144 GiB · Multi-GPU	140.0 GiB	142.0 GiB	Conditional · Tight fit
2 × RTX PRO 6000 Blackwell Max-Q192 GiB · Multi-GPU	140.0 GiB	190.0 GiB	Conditional · Room to spare
4 × RTX PRO 6000 Blackwell Max-Q384 GiB · Multi-GPU	140.0 GiB	380.0 GiB	Conditional · Room to spare
2 × Radeon AI PRO R970064 GiB · Multi-GPU	140.0 GiB	62.0 GiB	Conditional · Over capacity
4 × Radeon AI PRO R9700128 GiB · Multi-GPU	140.0 GiB	124.0 GiB	Conditional · Over capacity
2 × Arc Pro B7064 GiB · Multi-GPU	140.0 GiB	62.0 GiB	Conditional · Over capacity
4 × Arc Pro B70128 GiB · Multi-GPU	140.0 GiB	124.0 GiB	Conditional · Over capacity
2 × Instinct MI210 PCIe128 GiB · Multi-GPU	140.0 GiB	124.0 GiB	Conditional · Over capacity
2 × H200 NVL 141 GB PCIe282 GiB · Multi-GPU	140.0 GiB	278.0 GiB	Conditional · Room to spare
4 × H200 NVL 141 GB PCIe564 GiB · Multi-GPU	140.0 GiB	556.0 GiB	Conditional · Room to spare
GeForce RTX 3050 6 GB6 GiB · GPU	140.0 GiB	5.0 GiB	Over capacity
GeForce RTX 3050 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 3060 Ti 8 GB GDDR68 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 30708 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 3070 Ti8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
GeForce RTX 3080 10 GB10 GiB · GPU	140.0 GiB	9.0 GiB	Over capacity
GeForce RTX 3080 12 GB12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
GeForce RTX 3080 Ti12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Radeon RX 66008 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
Radeon RX 6600 XT8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
Radeon RX 6650 XT8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
Radeon RX 6700 XT12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Radeon RX 6750 XT12 GiB · GPU	140.0 GiB	11.0 GiB	Over capacity
Arc A750 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity
Arc A770 8 GB8 GiB · GPU	140.0 GiB	7.0 GiB	Over capacity

Architecture and calculation

Text decoding cache; runtime workspaces and optional speculative caches are additional.

62 full-attention layers × 8 KV heads × (128 key + 128 value dimensions).

Precision estimates need quantization scales and some higher-precision tensors. Backend support and actual file sizes vary. Whole-checkpoint counts can include auxiliary weights.

License: MiniMax M2.7 License. See the publisher’s terms.