MacBook Pro M3 Max 128GBBest value
D3.4 tok/s decode
~$2,499 MSRP
Can it run?
Very compromised
Using Q4_K_M in vLLM
Fit status
Very compromised
Decode
17.7 tok/s
TTFT
10910 ms
Safe context
13K
Memory
95.5 GB / 80.0 GB
Offload
20%
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 20.6 tok/s | 13686 ms | 23K |
| Chat | D | Very compromised | 19.2 tok/s | 5497 ms | 7K |
| Coding | D | Very compromised | 17.7 tok/s | 10910 ms | 13K |
| RAG | F | Too heavy | 20.6 tok/s | 17107 ms | 23K |
| Reasoning | D | Very compromised | 17.7 tok/s | 12894 ms | 13K |
How Command A 111B (111B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 43.3 GB | Low | C41 |
Q3_K_SBest for your GPU | 3 | 54.4 GB | Low | C44 |
ollama run command-a-111bhuggingface-cli download command-a-111bUpgrade options
~$2,499 MSRP
~$8,000 MSRP
| 4 |
62.2 GB |
| Medium |
| C44 |
Q4_K_M | 4 | 67.7 GB | Medium | C44 |
Q5_K_M | 5 | 79.9 GB | High | C44 |
Q6_K | 6 | 91.0 GB | High | F0 |
Q8_0 | 8 | 118.8 GB | Very High | F0 |
F16 | 16 | 227.6 GB | Maximum | F0 |
~$30,000 MSRP
~$30,000 MSRP