AMD Instinct MI350X 288GBBudget pick
C354.6 tok/s decode
~$8,000 MSRP
Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
33.8 tok/s
TTFT
5725 ms
Safe context
60K
Memory
49.5 GB / 184.3 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 33.8 tok/s | 8328 ms | 110K |
| Chat | C | Runs well | 33.8 tok/s | 3123 ms | 31K |
| Coding | C | Runs well | 33.8 tok/s | 5725 ms | 60K |
| RAG | C | Runs well | 33.8 tok/s | 10410 ms | 110K |
| Reasoning | C | Runs well | 33.8 tok/s | 6766 ms | 60K |
How gemma 3 27b it (27B params) fits at each quantization level on Mac Studio M3 Ultra 256GB (184.3 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 10.5 GB | Low | D31 |
Q3_K_S | 3 | 13.2 GB | Low | D31 |
NVFP4 | 4 | 15.1 GB | Medium | D31 |
Q4_K_M | 4 | 16.5 GB | Medium | D31 |
Q5_K_M | 5 | 19.4 GB | High | D32 |
Q6_K | 6 | 22.1 GB | High | D32 |
Q8_0 | 8 | 28.9 GB | Very High | D33 |
F16Best for your GPU | 16 | 55.4 GB | Maximum | D36 |
Upgrade options
~$8,000 MSRP
~$15,000 MSRP
H100 NVL 188GBBiggest leap