Granite 4.2 8B

Current dense Granite for reasoning, code and multilingual tools.

Stored parameters 8.8B
Native context 128Ktokens
ArchitectureDense
Use in calculator

Extended context: 524,288 tokens. Publisher advertises 512K extension from a 128K native context; requires validated long-context runtime settings.

Memory by precision and context

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

Weight precisionWeights8K total32K total128K total256K* total512K* total
Q4 · smaller4.97.210.925.945.985.9
Q5 · medium5.88.111.826.846.886.8
Q8 · larger8.710.914.729.749.789.7
FP16 / BF1616.418.922.737.757.797.7

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
HardwareMemory neededAvailableEstimateOpen plan
GeForce RTX 50508 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 50608 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 5060 Ti 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 5060 Ti 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 507012 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 5070 Ti16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 508016 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 509032 GiB · GPU7.2 GiB31.0 GiBRoom to spare
GeForce RTX 3060 12 GB12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 4060 Ti 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 4070 Ti SUPER16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 309024 GiB · GPU7.2 GiB23.0 GiBRoom to spare
GeForce RTX 3090 Ti24 GiB · GPU7.2 GiB23.0 GiBRoom to spare
GeForce RTX 409024 GiB · GPU7.2 GiB23.0 GiBRoom to spare
GeForce RTX 40608 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 4060 Ti 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 4070 GDDR6X12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 4070 SUPER12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 4070 Ti12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 408016 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 4080 SUPER16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 5090 Laptop GPU 24 GB24 GiB · GPU7.2 GiB23.0 GiBRoom to spare
GeForce RTX 5080 Laptop GPU 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 5070 Ti Laptop GPU 12 GB12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 5070 Laptop GPU 12 GB12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 5070 Laptop GPU 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 5060 Laptop GPU 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 5050 Laptop GPU 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 4090 Laptop GPU 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
GeForce RTX 4080 Laptop GPU 12 GB12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 4070 Laptop GPU 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 4060 Laptop GPU 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 4050 Laptop GPU 6 GB6 GiB · GPU7.2 GiB5.0 GiBOver capacity
RTX PRO 2000 Blackwell16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
RTX PRO 4000 Blackwell SFF24 GiB · GPU7.2 GiB23.0 GiBRoom to spare
RTX PRO 4000 Blackwell24 GiB · GPU7.2 GiB23.0 GiBRoom to spare
RTX PRO 4500 Blackwell Workstation32 GiB · GPU7.2 GiB31.0 GiBRoom to spare
RTX PRO 5000 Blackwell 48 GB48 GiB · GPU7.2 GiB47.0 GiBRoom to spare
RTX PRO 5000 Blackwell 72 GB72 GiB · GPU7.2 GiB71.0 GiBRoom to spare
RTX PRO 6000 Blackwell Workstation96 GiB · GPU7.2 GiB95.0 GiBRoom to spare
RTX PRO 6000 Blackwell Max-Q96 GiB · GPU7.2 GiB95.0 GiBRoom to spare
RTX A600048 GiB · GPU7.2 GiB47.0 GiBRoom to spare
RTX 6000 Ada Generation48 GiB · GPU7.2 GiB47.0 GiBRoom to spare
RTX 5000 Ada Generation32 GiB · GPU7.2 GiB31.0 GiBRoom to spare
A100 80 GB PCIe80 GiB · GPU7.2 GiB78.0 GiBRoom to spare
A100 80 GB SXM80 GiB · GPU7.2 GiB78.0 GiBRoom to spare
H100 80 GB SXM80 GiB · GPU7.2 GiB78.0 GiBRoom to spare
H100 NVL 94 GB PCIe94 GiB · GPU7.2 GiB92.0 GiBRoom to spare
H200 141 GB SXM141 GiB · GPU7.2 GiB139.0 GiBRoom to spare
H200 NVL 141 GB PCIe141 GiB · GPU7.2 GiB139.0 GiBRoom to spare
L40S48 GiB · GPU7.2 GiB46.0 GiBRoom to spare
B200 180 GB SXM180 GiB · GPU7.2 GiB178.0 GiBRoom to spare
B300 288 GB SXM288 GiB · GPU7.2 GiB286.0 GiBRoom to spare
A4048 GiB · GPU7.2 GiB46.0 GiBRoom to spare
Radeon RX 680016 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 6800 XT16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 6950 XT16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 7600 XT16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 7700 XT12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Radeon RX 7800 XT16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 7900 GRE16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 7900 XT20 GiB · GPU7.2 GiB19.0 GiBRoom to spare
Radeon RX 7900 XTX24 GiB · GPU7.2 GiB23.0 GiBRoom to spare
Radeon RX 9060 XT 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 9070 GRE12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Radeon RX 907016 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon RX 9070 XT16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Radeon AI PRO R970032 GiB · GPU7.2 GiB31.0 GiBRoom to spare
Radeon PRO W7800 32 GB32 GiB · GPU7.2 GiB31.0 GiBRoom to spare
Radeon PRO W7800 48 GB48 GiB · GPU7.2 GiB47.0 GiBRoom to spare
Radeon PRO W790048 GiB · GPU7.2 GiB47.0 GiBRoom to spare
Instinct MI210 PCIe64 GiB · GPU7.2 GiB62.0 GiBRoom to spare
Instinct MI300X OAM192 GiB · GPU7.2 GiB190.0 GiBRoom to spare
Instinct MI325X OAM256 GiB · GPU7.2 GiB254.0 GiBRoom to spare
Instinct MI350X OAM288 GiB · GPU7.2 GiB286.0 GiBRoom to spare
Instinct MI355X OAM288 GiB · GPU7.2 GiB286.0 GiBRoom to spare
Instinct MI350P PCIe144 GiB · GPU7.2 GiB142.0 GiBRoom to spare
Arc Pro B5016 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Arc Pro B6024 GiB · GPU7.2 GiB23.0 GiBRoom to spare
Arc Pro B6532 GiB · GPU7.2 GiB31.0 GiBRoom to spare
Arc Pro B7032 GiB · GPU7.2 GiB31.0 GiBRoom to spare
Arc A770 16 GB16 GiB · GPU7.2 GiB15.0 GiBRoom to spare
Arc B57010 GiB · GPU7.2 GiB9.0 GiBTight fit
Arc B58012 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Mac mini M1 · 8 GB (8-core GPU)8 GiB · Unified memory7.2 GiB6.0 GiBOver capacity
Mac mini M1 · 16 GB (8-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
Mac mini M2 · 8 GB (10-core GPU)8 GiB · Unified memory7.2 GiB6.0 GiBOver capacity
Mac mini M2 · 16 GB (10-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
Mac mini M2 · 24 GB (10-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
Mac mini M2 Pro · 16 GB (16-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
Mac mini M2 Pro · 32 GB (16-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac mini M2 Pro · 16 GB (19-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
Mac mini M2 Pro · 32 GB (19-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
MacBook Air M3 · 8 GB (8-core GPU)8 GiB · Unified memory7.2 GiB6.0 GiBOver capacity
MacBook Air M3 · 16 GB (8-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
MacBook Air M3 · 24 GB (8-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
MacBook Air M3 · 8 GB (10-core GPU)8 GiB · Unified memory7.2 GiB6.0 GiBOver capacity
MacBook Air M3 · 16 GB (10-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
MacBook Air M3 · 24 GB (10-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
MacBook Pro M1 Pro · 16 GB (16-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
MacBook Pro M1 Pro · 32 GB (16-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac Studio M1 Max · 32 GB (24-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac Studio M1 Max · 64 GB (24-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M1 Max · 32 GB (32-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac Studio M1 Max · 64 GB (32-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M1 Ultra · 64 GB (48-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M1 Ultra · 128 GB (48-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac Studio M1 Ultra · 64 GB (64-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M1 Ultra · 128 GB (64-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac Studio M2 Max · 32 GB (30-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac Studio M2 Max · 64 GB (30-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M2 Max · 32 GB (38-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac Studio M2 Max · 64 GB (38-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M2 Max · 96 GB (38-core GPU)96 GiB · Unified memory7.2 GiB72.0 GiBRoom to spare
Mac Studio M2 Ultra · 64 GB (60-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M2 Ultra · 128 GB (60-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac Studio M2 Ultra · 192 GB (60-core GPU)192 GiB · Unified memory7.2 GiB144.0 GiBRoom to spare
Mac Studio M2 Ultra · 64 GB (76-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M2 Ultra · 128 GB (76-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac Studio M2 Ultra · 192 GB (76-core GPU)192 GiB · Unified memory7.2 GiB144.0 GiBRoom to spare
MacBook Pro M3 Pro · 18 GB (18-core GPU)18 GiB · Unified memory7.2 GiB13.5 GiBRoom to spare
MacBook Pro M3 Pro · 36 GB (18-core GPU)36 GiB · Unified memory7.2 GiB27.0 GiBRoom to spare
MacBook Pro M3 Max · 36 GB (30-core GPU)36 GiB · Unified memory7.2 GiB27.0 GiBRoom to spare
MacBook Pro M3 Max · 96 GB (30-core GPU)96 GiB · Unified memory7.2 GiB72.0 GiBRoom to spare
MacBook Pro M3 Max · 48 GB (40-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
MacBook Pro M3 Max · 64 GB (40-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
MacBook Pro M3 Max · 128 GB (40-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac mini M4 · 16 GB (10-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
Mac mini M4 · 24 GB (10-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
Mac mini M4 · 32 GB (10-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Mac mini M4 Pro · 24 GB (16-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
Mac mini M4 Pro · 48 GB (16-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
Mac mini M4 Pro · 64 GB (16-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac mini M4 Pro · 24 GB (20-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
Mac mini M4 Pro · 48 GB (20-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
Mac mini M4 Pro · 64 GB (20-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M4 Max · 36 GB (32-core GPU)36 GiB · Unified memory7.2 GiB27.0 GiBRoom to spare
Mac Studio M4 Max · 48 GB (40-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
Mac Studio M4 Max · 64 GB (40-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Mac Studio M4 Max · 128 GB (40-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Mac Studio M3 Ultra · 96 GB (60-core GPU)96 GiB · Unified memory7.2 GiB72.0 GiBRoom to spare
Mac Studio M3 Ultra · 256 GB (60-core GPU)256 GiB · Unified memory7.2 GiB192.0 GiBRoom to spare
Mac Studio M3 Ultra · 96 GB (80-core GPU)96 GiB · Unified memory7.2 GiB72.0 GiBRoom to spare
Mac Studio M3 Ultra · 256 GB (80-core GPU)256 GiB · Unified memory7.2 GiB192.0 GiBRoom to spare
Mac Studio M3 Ultra · 512 GB (80-core GPU)512 GiB · Unified memory7.2 GiB384.0 GiBRoom to spare
MacBook Pro M5 · 16 GB (10-core GPU)16 GiB · Unified memory7.2 GiB12.0 GiBRoom to spare
MacBook Pro M5 · 24 GB (10-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
MacBook Pro M5 · 32 GB (10-core GPU)32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
MacBook Pro M5 Pro · 24 GB (16-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
MacBook Pro M5 Pro · 48 GB (16-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
MacBook Pro M5 Pro · 24 GB (20-core GPU)24 GiB · Unified memory7.2 GiB18.0 GiBRoom to spare
MacBook Pro M5 Pro · 48 GB (20-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
MacBook Pro M5 Pro · 64 GB (20-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
MacBook Pro M5 Max · 36 GB (32-core GPU)36 GiB · Unified memory7.2 GiB27.0 GiBRoom to spare
MacBook Pro M5 Max · 48 GB (40-core GPU)48 GiB · Unified memory7.2 GiB36.0 GiBRoom to spare
MacBook Pro M5 Max · 64 GB (40-core GPU)64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
MacBook Pro M5 Max · 128 GB (40-core GPU)128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Ryzen AI Max+ 395 · 32 GB32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Ryzen AI Max+ 395 · 64 GB64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Ryzen AI Max+ 395 · 128 GB128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Ryzen AI Max+ 392 · 32 GB32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Ryzen AI Max+ 392 · 64 GB64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Ryzen AI Max+ 392 · 128 GB128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
Ryzen AI Max+ 388 · 32 GB32 GiB · Unified memory7.2 GiB24.0 GiBRoom to spare
Ryzen AI Max+ 388 · 64 GB64 GiB · Unified memory7.2 GiB48.0 GiBRoom to spare
Ryzen AI Max+ 388 · 128 GB128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
NVIDIA DGX Spark · 128 GB128 GiB · Unified memory7.2 GiB96.0 GiBRoom to spare
2 × GeForce RTX 309048 GiB · Multi-GPU8.2 GiB46.0 GiBConditional · Room to spare
4 × GeForce RTX 309096 GiB · Multi-GPU10.2 GiB92.0 GiBConditional · Room to spare
2 × GeForce RTX 409048 GiB · Multi-GPU8.2 GiB46.0 GiBConditional · Room to spare
2 × GeForce RTX 509064 GiB · Multi-GPU8.2 GiB62.0 GiBConditional · Room to spare
4 × GeForce RTX 5090128 GiB · Multi-GPU10.2 GiB124.0 GiBConditional · Room to spare
2 × GeForce RTX 5060 Ti 16 GB32 GiB · Multi-GPU8.2 GiB30.0 GiBConditional · Room to spare
2 × RTX A600096 GiB · Multi-GPU8.2 GiB94.0 GiBConditional · Room to spare
2 × RTX PRO 5000 Blackwell 72 GB144 GiB · Multi-GPU8.2 GiB142.0 GiBConditional · Room to spare
2 × RTX PRO 6000 Blackwell Max-Q192 GiB · Multi-GPU8.2 GiB190.0 GiBConditional · Room to spare
4 × RTX PRO 6000 Blackwell Max-Q384 GiB · Multi-GPU10.2 GiB380.0 GiBConditional · Room to spare
2 × Radeon AI PRO R970064 GiB · Multi-GPU8.2 GiB62.0 GiBConditional · Room to spare
4 × Radeon AI PRO R9700128 GiB · Multi-GPU10.2 GiB124.0 GiBConditional · Room to spare
2 × Arc Pro B7064 GiB · Multi-GPU8.2 GiB62.0 GiBConditional · Room to spare
4 × Arc Pro B70128 GiB · Multi-GPU10.2 GiB124.0 GiBConditional · Room to spare
2 × Instinct MI210 PCIe128 GiB · Multi-GPU8.2 GiB124.0 GiBConditional · Room to spare
2 × H200 NVL 141 GB PCIe282 GiB · Multi-GPU8.2 GiB278.0 GiBConditional · Room to spare
4 × H200 NVL 141 GB PCIe564 GiB · Multi-GPU10.2 GiB556.0 GiBConditional · Room to spare
GeForce RTX 3050 6 GB6 GiB · GPU7.2 GiB5.0 GiBOver capacity
GeForce RTX 3050 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 3060 Ti 8 GB GDDR68 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 30708 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 3070 Ti8 GiB · GPU7.2 GiB7.0 GiBOver capacity
GeForce RTX 3080 10 GB10 GiB · GPU7.2 GiB9.0 GiBTight fit
GeForce RTX 3080 12 GB12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
GeForce RTX 3080 Ti12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Radeon RX 66008 GiB · GPU7.2 GiB7.0 GiBOver capacity
Radeon RX 6600 XT8 GiB · GPU7.2 GiB7.0 GiBOver capacity
Radeon RX 6650 XT8 GiB · GPU7.2 GiB7.0 GiBOver capacity
Radeon RX 6700 XT12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Radeon RX 6750 XT12 GiB · GPU7.2 GiB11.0 GiBRoom to spare
Arc A750 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity
Arc A770 8 GB8 GiB · GPU7.2 GiB7.0 GiBOver capacity

Architecture and calculation

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

  • 40 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: Apache 2.0. See the publisher’s terms.