Can the Apple M4 Max 40-core (64 GB) run NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball?
NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball·33B·Apple M4 Max 40-core (64 GB)·64 GB unified memory
Yes. The Apple M4 Max 40-core (64 GB) runs NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball fully in unified memory at Q8_0 (about 35 GB of 48 GB), at roughly 8.6 tokens/s.
- best quant
- Q8_0
- needs
- 35 GB
- usable
- 48 GB
- est. speed
- ~8.6 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball page →
Every quantisation of NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball on the Apple M4 Max 40-core (64 GB)
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 12 GB | fits | ~28 tok/s |
| Q3_K_M | 17 GB | fits | ~19 tok/s |
| Q4_K_M | 20 GB | fits | ~15 tok/s |
| Q5_K_M | 24 GB | fits | ~13 tok/s |
| Q6_K | 28 GB | fits | ~11 tok/s |
| Q8_0 pick | 35 GB | fits | ~8.6 tok/s |
| FP16 / BF16 | 65 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (546 GB/s); prompt processing and long contexts are slower.
Measured speed on the Apple M4 Max 40-core (64 GB)
No community reports for this pair yet.
Report your own speed →Omni models that fit the Apple M4 Max 40-core (64 GB) comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 35.3BA3B | Q8_0 | ≈33 GBFits in memory | ~94 tok/s | |
| 33BA3B | Q8_0 | ≈34 GBFits in memory | ~94 tok/s | |
| 31.7BA3B | Q8_0 | ≈33 GBFits in memory | ~94 tok/s | |
| 31.7BA3B | Q8_0 | ≈34 GBFits in memory | ~94 tok/s | |
| 24.3B | Q8_0 | ≈26 GBFits in memory | ~12 tok/s | |
| 33.5B | Q8_0 | ≈37 GBFits in memory | ~8.4 tok/s |
Other GPUs that run NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball
Frequently asked questions
- Can the Apple M4 Max 40-core (64 GB) run NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball?
- Yes. The Apple M4 Max 40-core (64 GB) runs NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball fully in unified memory at Q8_0 (about 35 GB of 48 GB), at roughly 8.6 tokens/s.
- How fast does NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball run on the Apple M4 Max 40-core (64 GB)?
- An estimate from memory bandwidth gives about 8.6 tokens/s at Q8_0.
- Which quantisation of NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball should I use on the Apple M4 Max 40-core (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.