Can the Apple M4 (16 GB) run lumi-4b?
lumi-4b·4B·Apple M4 (16 GB)·16 GB unified memory
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)
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~51 tok/s |
| Q3_K_M | 3.7 GB | fits | ~34 tok/s |
| Q4_K_M | 4.2 GB | fits | ~27 tok/s |
| Q5_K_M | 4.6 GB | fits | ~23 tok/s |
| Q6_K | 5.7 GB | fits | ~20 tok/s |
| Q8_0 | 5.9 GB | fits | ~16 tok/s |
| FP16 / BF16 pick | 9.6 GB | fits | ~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-server -hf Mateus-Nery/lumi-4b-GGUF:BF16brew 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 →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~15 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~19 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~16 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~15 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~15 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~20 tok/s |
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.