MacBook Pro M3 Max 128GBBest value
D3.4 tok/s decode
~$2,499 MSRP
Can it run?
Too heavy
Using Q4_K_M in vLLM
Fit status
Too heavy
Decode
2.9 tok/s
TTFT
67224 ms
Safe context
4K
Memory
89.9 GB / 24.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 2.9 tok/s | 97780 ms | 7K |
| Chat | F | Too heavy | 2.9 tok/s | 36668 ms | 4K |
| Coding | F | Too heavy | 2.9 tok/s | 67224 ms | 4K |
| RAG | F | Too heavy | 2.9 tok/s | 122225 ms | 7K |
| Reasoning | F | Too heavy | 2.9 tok/s | 79446 ms | 4K |
How Command A 111B (111B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 43.3 GB | Low | F0 |
Q3_K_S | 3 | 54.4 GB | Low | F0 |
NVFP4 | 4 | 62.2 GB | Medium | F0 |
Q4_K_M | 4 | 67.7 GB | Medium | F0 |
Q5_K_M | 5 | 79.9 GB | High | F0 |
Q6_K | 6 | 91.0 GB | High | F0 |
Q8_0 | 8 | 118.8 GB | Very High | F0 |
F16 | 16 | 227.6 GB | Maximum | F0 |
Upgrade options
~$2,499 MSRP
~$8,000 MSRP
NVIDIA H200 141GBBiggest leap~$30,000 MSRP
NVIDIA H200 PCIe 141GBNVIDIA upgrade~$30,000 MSRP