MacBook Pro M3 Max 128GBBest value
C9.6 tok/s decode
~$2,499 MSRP
Can it run?
Too heavy
Using Q4_K_M in vLLM
Fit status
Too heavy
Decode
24.0 tok/s
TTFT
8063 ms
Safe context
5K
Memory
78.4 GB / 24.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 24.0 tok/s | 11728 ms | 10K |
| Chat | F | Too heavy | 24.0 tok/s | 4398 ms | 4K |
| Coding | F | Too heavy | 24.0 tok/s | 8063 ms | 5K |
| RAG | F | Too heavy | 24.0 tok/s | 14660 ms | 10K |
| Reasoning | F | Too heavy | 24.0 tok/s | 9529 ms | 5K |
How Mistral Small 4 119B (119B params) fits at each quantization level on RTX A5500 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | F0 |
Q3_K_S | 3 | 58.3 GB | Low | F0 |
NVFP4 | 4 | 66.6 GB | Medium | F0 |
Q4_K_M | 4 | 72.6 GB | Medium | F0 |
Q5_K_M | 5 | 85.7 GB | High | F0 |
Q6_K | 6 | 97.6 GB | High | F0 |
Q8_0 | 8 | 127.3 GB | Very High | F0 |
F16 | 16 | 244.0 GB | Maximum | F0 |
Upgrade options
~$2,499 MSRP
~$8,000 MSRP
NVIDIA H200 141GBNVIDIA upgrade~$30,000 MSRP
Gaudi 3 128GBBiggest leap