Nemotron 3 Nano 30B needs ~31.5 GB VRAM. NVIDIA H20 96GB has 96.0 GB. With Q4_K_M quantization, expect ~177 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
190.3 tok/s
TTFT
1017 ms
Safe context
131K
Memory
31.5 GB / 96.0 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 | S | Runs well | 177.0 tok/s | 596 ms | 131K |
| Coding | S | Runs well | 177.0 tok/s | 1093 ms | 131K |
| Agentic Coding | S | Runs well | 177.0 tok/s | 1591 ms | 131K |
| Reasoning | S | Runs well | 177.0 tok/s | 1292 ms | 131K |
| RAG | S | Runs well | 177.0 tok/s | 1988 ms | 131K |
How Nemotron 3 Nano 30B (30B params) fits at each quantization level on NVIDIA H20 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | A80 |
Q3_K_S | 3 | 14.7 GB | Low | A80 |
NVFP4 | 4 |
Copy-paste commands to run Nemotron 3 Nano 30B on your machine.
Run
ollama run nemotron-nano:30bYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 47 tok/s | ||
| 30.5B | S |
Yes, NVIDIA H20 96GB can run Nemotron 3 Nano 30B with a S grade (Runs well). Expected decode speed: 177.0 tok/s.
Nemotron 3 Nano 30B (30B parameters) requires approximately 31.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Nemotron 3 Nano 30B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H20 96GB, Nemotron 3 Nano 30B achieves approximately 177.0 tokens per second decode speed with a time-to-first-token of 1093ms using Q4_K_M quantization.
For coding workloads, Nemotron 3 Nano 30B on NVIDIA H20 96GB receives a S grade with 177.0 tok/s and 131K context.
On NVIDIA H20 96GB, Nemotron 3 Nano 30B can safely use up to 131K tokens of context. The model's official context limit is 131K, 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/nemotron-3-nano-30b-on-h20-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
16.8 GB |
| Medium |
| A80 |
Q4_K_M | 4 | 18.3 GB | Medium | A81 |
Q5_K_M | 5 | 21.6 GB | High | A81 |
Q6_K | 6 | 24.6 GB | High | A81 |
Q8_0 | 8 | 32.1 GB | Very High | A83 |
F16Best for your GPU | 16 | 61.5 GB | Maximum | S88 |
| 489.9 tok/s |
| 122B | S | 130.3 tok/s |
| 35B | S | 411.7 tok/s |
| 35B | S | 447.8 tok/s |