Apple M4 Max meets the minimum VRAM requirement for Q4 inference of codellama/CodeLlama-34b-hf. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.
Apple M4 Max can run codellama/CodeLlama-34b-hf with Q4 quantization. At approximately 27 tokens/second, you can expect Moderate speed - useful for batch processing.
You have 111GB headroom, which is sufficient for system overhead and smooth operation.
| Quantization | VRAM needed | VRAM available | Estimated speed | Verdict |
|---|---|---|---|---|
| Q4 | 17GB | 128GB | 27.27 tok/s | ✅ Fits comfortably |
| Q8 | 35GB | 128GB | 17.68 tok/s | ✅ Fits comfortably |
| FP16 | 70GB | 128GB | 10.22 tok/s | ✅ Fits comfortably |