Nemotron Cascade 2 30B A3B needs ~24.5 GB VRAM. RTX 3090 Ti 24GB has 24.0 GB. With Q4_K_M quantization, expect ~79 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
0.5 GB over capacity — needs offload or smaller quantization
Fit status
Runs with offload (needs ~0.4 GB host RAM)
Decode
79.2 tok/s
TTFT
2443 ms
Safe context
13K
Memory
24.5 GB / 24.0 GB
This setup is broadly balanced for this model.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs with offload | 110.6 tok/s | 954 ms | 13K |
| Coding | S | Runs with offload (needs ~0.4 GB host RAM) | 79.2 tok/s | 2443 ms | 13K |
| Agentic Coding | A | Very compromised (needs ~2.3 GB host RAM) | 62.5 tok/s | 4506 ms | 13K |
| Reasoning | S | Runs with offload (needs ~0.4 GB host RAM) | 79.2 tok/s | 2887 ms | 13K |
| RAG | A | Very compromised (needs ~2.3 GB host RAM) | 62.5 tok/s |
How Nemotron Cascade 2 30B A3B (30B params) fits at each quantization level on RTX 3090 Ti 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | S88 |
Q3_K_S | 3 | 14.7 GB | Low | S88 |
NVFP4 | 4 |
Copy-paste commands to run Nemotron Cascade 2 30B A3B on your machine.
Run
ollama run nemotron-cascade-2Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 30.5B | S | 71.4 tok/s | ||
| 35B | A | 46.6 tok/s |
Yes, RTX 3090 Ti 24GB can run Nemotron Cascade 2 30B A3B with a S grade (Runs with offload (needs ~0.4 GB host RAM)). Expected decode speed: 79.2 tok/s.
Nemotron Cascade 2 30B A3B (30B parameters) requires approximately 24.5 GB of memory with Q4_K_M quantization.
The recommended quantization for Nemotron Cascade 2 30B A3B is Q4_K_M, which balances quality and memory efficiency.
On RTX 3090 Ti 24GB, Nemotron Cascade 2 30B A3B achieves approximately 79.2 tokens per second decode speed with a time-to-first-token of 2443ms using Q4_K_M quantization.
For coding workloads, Nemotron Cascade 2 30B A3B on RTX 3090 Ti 24GB receives a S grade with 79.2 tok/s and 13K context.
On RTX 3090 Ti 24GB, Nemotron Cascade 2 30B A3B can safely use up to 13K tokens of context. The model's official context limit is 262K, 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-cascade-2-30b-a3b-on-rtx-3090-ti-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| 5632 ms |
| 13K |
16.8 GB |
| Medium |
| S87 |
Q4_K_MBest for your GPU | 4 | 18.3 GB | Medium | S87 |
Q5_K_M | 5 | 21.6 GB | High | F0 |
Q6_K | 6 | 24.6 GB | High | F0 |
Q8_0 | 8 | 32.1 GB | Very High | F0 |
F16 | 16 | 61.5 GB | Maximum | F0 |
| 35B | A | 62.1 tok/s |
| 32B | A | 14.7 tok/s |
| 30.5B | S | 71.4 tok/s |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.