WizardLM 13B needs ~22.6 GB but RX 9060 XT 16GB only has 16.0 GB. Try a smaller quantization or lighter model.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
6.6 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
9.2 tok/s
TTFT
21079 ms
Safe context
7K
Memory
22.6 GB / 16.0 GB
Offload
30%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 22.6 GB, but this setup only exposes 16.0 GB of usable VRAM.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs with offload (needs ~0.3 GB host RAM) | 17.8 tok/s | 5934 ms | 7K |
| Coding | F | Too heavy | 9.2 tok/s | 21079 ms | 7K |
| Agentic Coding | F | Too heavy | 3.8 tok/s | 73846 ms | 7K |
| Reasoning | F | Too heavy | 9.2 tok/s | 24911 ms | 7K |
| RAG | F | Too heavy | 3.8 tok/s | 92307 ms | 7K |
How WizardLM 13B (13B params) fits at each quantization level on RX 9060 XT 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B70 |
Q3_K_S | 3 | 6.4 GB | Low | A71 |
NVFP4 | 4 | 7.3 GB | Medium | A72 |
Q4_K_M | 4 | 7.9 GB | Medium | A72 |
Q5_K_M | 5 | 9.4 GB | High | A72 |
Q6_KBest for your GPU | 6 | 10.7 GB | High | A72 |
Q8_0 | 8 | 13.9 GB | Very High | F0 |
F16 | 16 | 26.7 GB | Maximum | F0 |
アップグレードオプション
Makes the model fit on the accelerator instead of staying completely out of reach.
Raises estimated decode speed by about 266%.
〜$899 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$999 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
〜$1,899 MSRP
No, WizardLM 13B requires more memory than RX 9060 XT 16GB provides.
WizardLM 13B (13B parameters) requires approximately 22.6 GB of memory with Q4_K_M quantization.
The recommended quantization for WizardLM 13B is Q4_K_M, which balances quality and memory efficiency.
On RX 9060 XT 16GB, WizardLM 13B achieves approximately 9.2 tokens per second decode speed with a time-to-first-token of 21079ms using Q4_K_M quantization.
For coding workloads, WizardLM 13B on RX 9060 XT 16GB receives a F grade with 9.2 tok/s and 7K context.
On RX 9060 XT 16GB, WizardLM 13B can safely use up to 7K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/wizardlm-13b-on-rx-9060-xt-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
