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.

tencent logo

Can the Apple M1 Max (64 GB) run Hy-SimulMT-30B-A3B?

Hy-SimulMT-30B-A3B·30.4B (3B active)·Apple M1 Max (64 GB)·64 GB unified memory

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

Yes. The Apple M1 Max (64 GB) runs Hy-SimulMT-30B-A3B fully in unified memory at Q8_0 (about 37 GB of 48 GB).

best quant
Q8_0
needs
37 GB
usable
48 GB

Estimates from the model's size.Try other contexts on the Hy-SimulMT-30B-A3B page →

Every quantisation of Hy-SimulMT-30B-A3B on the Apple M1 Max (64 GB)

QuantMemoryFit
Q4_K_M 21 GBfits
Q8_0 pick37 GBfits
FP16 / BF16 68 GBtoo big

Speed is a bandwidth-based estimate for generating text (400 GB/s); prompt processing and long contexts are slower.

Run Hy-SimulMT-30B-A3B on the Apple M1 Max (64 GB)

Transformers · Run with the translation pipelinedocs
from transformers import pipeline

pipe = pipeline("translation", model="tencent/Hy-SimulMT-30B-A3B")
result = pipe("Self-hosting puts you in control of your data.")
print(result)

Translation models that fit the Apple M1 Max (64 GB) comfortably

All that fit →
ModelParamsBest quantMemoryLicence
30.1BA3BQ8_0≈36 GBFits in memoryCommercial OK
31.8BQ8_0≈38 GBFits in memoryConditions
9.7BFP16 / BF16≈22 GBFits in memoryCommercial OK
tencent logoHy-MT2-7Btencent
8BFP16 / BF16≈18 GBFits in memoryCommercial OK
8BFP16 / BF16≈18 GBFits in memoryCheck licence
8.5BFP16 / BF16≈20 GBFits in memoryConditions

Other GPUs that run Hy-SimulMT-30B-A3B

Frequently asked questions

Can the Apple M1 Max (64 GB) run Hy-SimulMT-30B-A3B?
Yes. The Apple M1 Max (64 GB) runs Hy-SimulMT-30B-A3B fully in unified memory at Q8_0 (about 37 GB of 48 GB).
Which quantisation of Hy-SimulMT-30B-A3B should I use on the Apple M1 Max (64 GB)?
Q8_0: 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.