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 M4 Pro (48 GB) run WeMM-Video-35BA3B?

WeMM-Video-35BA3B·36.2B (5B active)·Apple M4 Pro (48 GB)·48 GB unified memory

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

Yes. The Apple M4 Pro (48 GB) runs WeMM-Video-35BA3B fully in unified memory at Q6_K (about 30 GB of 36 GB), at roughly 37 tokens/s.

best quant
Q6_K
needs
30 GB
usable
36 GB
est. speed
~37 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeMM-Video-35BA3B page →

Every quantisation of WeMM-Video-35BA3B on the Apple M4 Pro (48 GB)

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~92 tok/s
Q3_K_M Noticeable loss18 GBfits~62 tok/s
Q4_K_M Small loss23 GBfits~50 tok/s
Q5_K_M Near-lossless26 GBfits~42 tok/s
Q6_K pickNear-lossless30 GBfits~37 tok/s
Q8_0 Lossless39 GBtoo big—
FP16 / BF16 Lossless72 GBtoo big—

Speed is a bandwidth-based estimate for generating text (273 GB/s); prompt processing and long contexts are slower.

Measured speed on the Apple M4 Pro (48 GB)

No community reports for this pair yet.

Report your own speed →

Vision models that fit the Apple M4 Pro (48 GB) comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
36BA3BQ6_K≈30 GBFits in memory~61 tok/sCommercial OK
36BA3BQ6_K≈29 GBFits in memory~61 tok/sCommercial OK
31.3BQ6_K≈33 GBFits in memory~5.8 tok/sCommercial OK
27.8BQ8_0≈31 GBFits in memory~5.1 tok/sCommercial OK
35.2BA3BQ6_K≈29 GBFits in memory~61 tok/sCommercial OK
meta-models logoMuse-Glimmer-30Bmeta-models
29.8BQ8_0≈30 GBFits in memory~4.7 tok/sCommercial OK

Other GPUs that run WeMM-Video-35BA3B

Frequently asked questions

Can the Apple M4 Pro (48 GB) run WeMM-Video-35BA3B?
Yes. The Apple M4 Pro (48 GB) runs WeMM-Video-35BA3B fully in unified memory at Q6_K (about 30 GB of 36 GB), at roughly 37 tokens/s.
How fast does WeMM-Video-35BA3B run on the Apple M4 Pro (48 GB)?
An estimate from memory bandwidth gives about 37 tokens/s at Q6_K.
Which quantisation of WeMM-Video-35BA3B should I use on the Apple M4 Pro (48 GB)?
Q6_K: the largest one that fits. Expected quality: near-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.