RX 7900 XTX 24GBBest value
C41.5 tok/s decode
~$999 MSRP
Can it run?
Too heavy
Using Q4_K_M in Ollama
Fit status
Too heavy
Decode
3.9 tok/s
TTFT
49055 ms
Safe context
8K
Memory
23.6 GB / 11.5 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 3.9 tok/s | 71353 ms | 13K |
| Chat | F | Too heavy | 3.9 tok/s | 26757 ms | 4K |
| Coding | F | Too heavy | 3.9 tok/s | 49055 ms | 8K |
| RAG | F | Too heavy | 3.9 tok/s | 89191 ms | 13K |
| Reasoning | F | Too heavy | 3.9 tok/s | 57974 ms | 8K |
How gemma 3 27b it (27B params) fits at each quantization level on MacBook Air M2 16GB (11.5 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 10.5 GB | Low | C44 |
Q3_K_S | 3 | 13.2 GB | Low | F0 |
NVFP4 | 4 | 15.1 GB | Medium | F0 |
Q4_K_M | 4 | 16.5 GB | Medium | F0 |
Q5_K_M | 5 | 19.4 GB | High | F0 |
Q6_K | 6 | 22.1 GB | High | F0 |
Q8_0 | 8 | 28.9 GB | Very High | F0 |
F16 | 16 | 55.4 GB | Maximum | F0 |
Upgrade options
~$999 MSRP
~$1,099 MSRP
RTX 5090 32GBBiggest leap~$1,999 MSRP
~$2,499 MSRP