Can the Apple M4 (16 GB) run WeVisCut?
WeVisCut·9.4B·Apple M4 (16 GB)·16 GB unified memory
Yes. The Apple M4 (16 GB) runs WeVisCut fully in unified memory at Q6_K (about 8.7 GB of 11 GB), at roughly 8.5 tokens/s.
- best quant
- Q6_K
- needs
- 8.7 GB
- usable
- 11 GB
- est. speed
- ~8.5 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the WeVisCut page →
Every quantisation of WeVisCut on the Apple M4 (16 GB)
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.5 GB | fits | ~21 tok/s |
| Q3_K_M | 6.0 GB | fits | ~14 tok/s |
| Q4_K_M | 7.0 GB | fits | ~12 tok/s |
| Q5_K_M | 7.8 GB | fits | ~9.9 tok/s |
| Q6_K pick | 8.7 GB | fits | ~8.5 tok/s |
| Q8_0 | 11 GB | too big | — |
| FP16 / BF16 | 19 GB | too big | — |
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 WeVisCut on the Apple M4 (16 GB)
Using Q6_K, the best fit for Apple M4 (16 GB).
llama-server -hf prithivMLmods/tencent-WeVisCut-GGUF:Q6_Kbrew install llama.cpp ships with Metal. Downloads the GGUF on first run.
Omni models that fit the Apple M4 (16 GB) comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 9.4B | Q8_0 | ≈10 GBFits in memory | ~6.6 tok/s | |
| 8B | Q8_0 | ≈9.2 GBFits in memory | ~7.8 tok/s | |
| 10.7B | Q8_0 | ≈8.9 GBFits in memory | ~5.8 tok/s | |
| 9.1B | Q8_0 | ≈10 GBFits in memory | ~6.9 tok/s | |
| 8.3B | Q8_0 | ≈10 GBFits in memory | ~7.5 tok/s | |
| 8.7B | Q8_0 | ≈8.9 GBFits in memory | ~7.2 tok/s |
Other GPUs that run WeVisCut
Frequently asked questions
- Can the Apple M4 (16 GB) run WeVisCut?
- Yes. The Apple M4 (16 GB) runs WeVisCut fully in unified memory at Q6_K (about 8.7 GB of 11 GB), at roughly 8.5 tokens/s.
- How fast does WeVisCut run on the Apple M4 (16 GB)?
- An estimate from memory bandwidth gives about 8.5 tokens/s at Q6_K.
- Which quantisation of WeVisCut should I use on the Apple M4 (16 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.