RX 7900 XT 20GBBudget pick
C98.4 tok/s decode
~$899 MSRP
Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
44.9 tok/s
TTFT
4316 ms
Safe context
29K
Memory
8.9 GB / 16.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 44.9 tok/s | 6278 ms | 50K |
| Chat | C | Runs well | 44.9 tok/s | 2354 ms | 15K |
| Coding | C | Runs well | 44.9 tok/s | 4316 ms | 29K |
| RAG | C | Runs well | 44.9 tok/s | 7848 ms | 50K |
| Reasoning | C | Runs well | 44.9 tok/s | 5101 ms | 29K |
How llava llama 3 8b v1 1 (8B params) fits at each quantization level on RTX 2000 Ada 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | D34 |
Q3_K_S | 3 | 3.9 GB | Low | D35 |
NVFP4 | 4 | 4.5 GB | Medium | D36 |
Q4_K_M | 4 | 4.9 GB | Medium | D36 |
Q5_K_M | 5 | 5.8 GB | High | D37 |
Q6_K | 6 | 6.6 GB | High | D38 |
Q8_0Best for your GPU | 8 | 8.6 GB | Very High | C41 |
F16 | 16 | 16.4 GB | Maximum | F0 |
Upgrade options
~$899 MSRP
~$1,999 MSRP
RTX A4500 20GBBiggest leap