selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

ceia-br logo

Can the Apple M4 (16 GB) run lumi-4b?

lumi-4b·4B·Apple M4 (16 GB)·16 GB unified memory

Saved in this browser, used on every model page.
Yes

Yes. The Apple M4 (16 GB) runs lumi-4b fully in unified memory at FP16 / BF16 (about 9.6 GB of 11 GB), at roughly 8.3 tokens/s.

best quant
FP16 / BF16
needs
9.6 GB
usable
11 GB
est. speed
~8.3 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the lumi-4b page →

Every quantisation of lumi-4b on the Apple M4 (16 GB)

QuantQualityMemoryFitSpeed
Q2_K Heavy loss3.1 GBfits~51 tok/s
Q3_K_M Noticeable loss3.7 GBfits~34 tok/s
Q4_K_M Small loss4.2 GBfits~27 tok/s
Q5_K_M Near-lossless4.6 GBfits~23 tok/s
Q6_K Near-lossless5.7 GBfits~20 tok/s
Q8_0 Lossless5.9 GBfits~16 tok/s
FP16 / BF16 pickLossless9.6 GBfits~8.3 tok/s

Speed is a bandwidth-based estimate for generating text (120 GB/s); prompt processing and long contexts are slower.

Measured speed on the Apple M4 (16 GB)

No community reports for this pair yet.

Report your own speed →

Run lumi-4b on the Apple M4 (16 GB)

Using FP16 / BF16, the best fit for Apple M4 (16 GB).

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf Mateus-Nery/lumi-4b-GGUF:BF16

brew install llama.cpp ships with Metal. Downloads the GGUF on first run.

Chat models that fit the Apple M4 (16 GB) comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
4BQ8_0≈5.8 GBFits in memory~15 tok/sCommercial OK
3.2BQ8_0≈4.7 GBFits in memory~19 tok/sConditions
3.8BQ8_0≈5.5 GBFits in memory~16 tok/sCommercial OK
4BQ8_0≈5.8 GBFits in memory~15 tok/sCommercial OK
4.1BQ8_0≈5.9 GBFits in memory~15 tok/sCommercial OK
3.1BQ8_0≈4.3 GBFits in memory~20 tok/sNon-commercial

Other GPUs that run lumi-4b

Frequently asked questions

Can the Apple M4 (16 GB) run lumi-4b?
Yes. The Apple M4 (16 GB) runs lumi-4b fully in unified memory at FP16 / BF16 (about 9.6 GB of 11 GB), at roughly 8.3 tokens/s.
How fast does lumi-4b run on the Apple M4 (16 GB)?
An estimate from memory bandwidth gives about 8.3 tokens/s at FP16 / BF16.
Which quantisation of lumi-4b should I use on the Apple M4 (16 GB)?
FP16 / BF16: the largest one that fits. Expected quality: lossless compared with the full-precision weights.

Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.