GeForce RTX 4070 (AD103)

10de:2709 · AD103 · measured

Status and notes

Then-untested AD103 die. The register-level probe went from half to full rate and doubled FP16/BF16 with FP32 accumulate; cuBLAS GEMM gained less on small shapes (+43% at 1024, rising to +50% at 4096) because those runs are not tensor-bound.

Measured throughput

46 SMs · driver 595.99.02

Mode	Stock	Unlocked	Gain
`f16/f16`	132.60 TF/s	132.20 TF/s	1.00×
`f16/f32`	66.30 TF/s	132.20 TF/s	1.99×
`bf16/f32`	66.30 TF/s	132.00 TF/s	1.99×
`s8/s32`	265.10 TOP/s	263.70 TOP/s	0.99×
`dp4a`	65.80 TOP/s	65.70 TOP/s	1.00×
`ffma`	31.70 TF/s	31.70 TF/s	1.00×
`tf32`	33.10 TF/s	65.80 TF/s	1.99×
`u4/s32`	527.20 TOP/s	525.70 TOP/s	1.00×
`cuBLAS f16/f32 1024³`	49.06 TF/s	70.14 TF/s	1.43×
`cuBLAS f16/f32 4096³`	64.04 TF/s	96.33 TF/s	1.50×
`cuBLAS f16/f32 8192³`	64.42 TF/s	93.63 TF/s	1.45×

Same card, same binary, stock versus unlocked. Modes that did not change are reported too — an unlock that does not move a path is a fact worth having.

Sources

JustAResearcher/gpu-unlock-ada/blob/main/docs/ada-2709-report.md

How to install · All cards