Can Inkling Small run on iPhone 14?

NOWon't fit
Formula estimate

What this means

None of the versions we checked fit safely on this phone. The checked version needs about 190.5 GB, while we estimate that the model can use about 3.9 GB.

Try a smaller model, or use this model on a device with more memory.

This result is calculated from the phone and model specifications. It has not been measured on this exact phone and setup.

−186.6GB short
memory that doesn't exist here
190.5GB
needed at Q4_K_M
Q4_K_M
quant checked
needs 190.5 GBusable 3.9 GB · short 186.6 GB
Apple A15 Bionic6 GB RAMMetal

Three ways forward

1
Try a smaller quant
No quant of Inkling Small fits this phone — even the smallest is too big. Options 2 and 3 are your real choices.
2
Best model that fits
Qwen3 0.6B · Q8_0 · 0.6 GB
~25.6 tokens/s here
check Qwen3 0.6B
3
Run it in the cloud
The full Inkling Small, no download, at data-center speed — pay per token.
provider recommendations coming later

Where the memory goes

ComponentDetailGB
Model weightsQ4_K_M GGUF (162.5 GB) + mmap overhead170.6
KV cache4K context window19.3
Runtimellama.cpp + app overhead0.6
Total neededat Q4_K_M, 4K context190.5
Working budget6 GB RAM iOS reserve (jetsam limit)3.9
Headroommemory shortfall−186.6

Pick your quant

QuantDownloadVerdictSpeed
IQ1_S 74.8 GB Won't fitwon't fit
Q3_K_M 119.4 GB Won't fitwon't fit
IQ4_XS 127.4 GB Won't fitwon't fit
Q4_K_S 152.3 GB Won't fitwon't fit
MXFP4 158 GB Won't fitwon't fit
Q4_K_M 162.5 GB Won't fitwon't fit
Q5_K_M 196.1 GB Won't fitwon't fit
Q6_K 218.9 GB Won't fitwon't fit
Q8_0 280.3 GB Won't fitwon't fit

Related checks

More on iPhone 14
Qwen3 0.6BLlama 3.2 1BGemma 3 1BTernary Bonsai 1.7BOvisOCR2 0.8B
Inkling Small on other phones
Galaxy S25 UltraGalaxy S25Galaxy S24 UltraGalaxy S24Galaxy S23 Ultra