Runtime API error after installing 2.3 cudaSafeCall(): out of memory

Accelerated Computing CUDA CUDA Programming and Performance
1

After installing the 2.3.0 driver (not without problems, but solved in “keep having to reinstall cuda driver”), when I run some binaries from the SDK I get a error like

Douglas:~ douglasaguiar$ "/Developer/GPU Computing/C/bin/darwin/release/histogram"

Initializing data...

...allocating CPU memory.

...generating input data

...allocating GPU memory and copying input data

cudaSafeCall() Runtime API error in file <main.cpp>, line 64 : out of memory.

this error goes on on the binaries:

    [*]bandwidthTest

    [*]fastWalshTransform

    [*]simpleMultiGPU

    [*]simpleStreams

and others that I did not test.

Does somebody have any ideas what can be causing this “out of memory”??

Thanks.

Macbook Pro, Core 2 Duo 2.2GHz - GeForce 8600M GT 128MB