WizardLM 13B needs ~25.8 GB VRAM. NVIDIA L20 48GB has 48.0 GB. With Q4_K_M quantization, expect ~84 tok/s.
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
Fit status
Runs well
Decode
83.5 tok/s
TTFT
2318 ms
Safe context
8K
Memory
25.8 GB / 48.0 GB
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 83.5 tok/s | 1264 ms | 8K |
| Coding | A | Runs well | 83.5 tok/s | 2318 ms | 8K |
| Agentic Coding | A | Runs well | 83.5 tok/s | 3372 ms | 8K |
| Reasoning | A | Runs well | 83.5 tok/s | 2740 ms | 8K |
| RAG | A | Runs well | 83.5 tok/s | 4215 ms | 8K |
How WizardLM 13B (13B params) fits at each quantization level on NVIDIA L20 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.1 GB | Low | B62 |
Q3_K_S | 3 | 6.4 GB | Low | B63 |
NVFP4 | 4 |
Copy-paste commands to run WizardLM 13B on your machine.
Run
lms load WizardLM-13B-V1.0 && lms server startYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 68.7 tok/s | ||
| 27B | S | 28.6 tok/s |
Yes, NVIDIA L20 48GB can run WizardLM 13B with a A grade (Runs well). Expected decode speed: 83.5 tok/s.
WizardLM 13B (13B parameters) requires approximately 25.8 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 NVIDIA L20 48GB, WizardLM 13B achieves approximately 83.5 tokens per second decode speed with a time-to-first-token of 2318ms using Q4_K_M quantization.
For coding workloads, WizardLM 13B on NVIDIA L20 48GB receives a A grade with 83.5 tok/s and 8K context.
On NVIDIA L20 48GB, WizardLM 13B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/wizardlm-13b-on-l20-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
7.3 GB |
| Medium |
| B63 |
Q4_K_M | 4 | 7.9 GB | Medium | B63 |
Q5_K_M | 5 | 9.4 GB | High | B63 |
Q6_K | 6 | 10.7 GB | High | B64 |
Q8_0 | 8 | 13.9 GB | Very High | B65 |
F16Best for your GPU | 16 | 26.7 GB | Maximum | B69 |
| 27B | S | 18.8 tok/s |
| 35B | S | 85.8 tok/s |
| 30B | S | 98.6 tok/s |