Apple M4 Max meets the minimum VRAM requirement for Q4 inference of trl-internal-testing/tiny-LlamaForCausalLM-3.2. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Max can run trl-internal-testing/tiny-LlamaForCausalLM-3.2 with Q4 quantization. At approximately 69 tokens/second, you can expect Good speed - acceptable for interactive use.
You have 124GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 4GB | 128GB | 69.02 tok/s | ✅ Fits comfortably |
| Q8 | 7GB | 128GB | 47.51 tok/s | ✅ Fits comfortably |
| FP16 | 15GB | 128GB | 26.21 tok/s | ✅ Fits comfortably |