Granite 4.1 30B needs ~31.4 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~165 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
165.3 tok/s
TTFT
1171 ms
Safe context
131K
Memory
31.4 GB / 80.0 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 | 165.3 tok/s | 639 ms | 131K |
| Coding | A | Runs well | 165.3 tok/s | 1171 ms | 131K |
| Agentic Coding | A | Runs well | 165.3 tok/s | 1704 ms | 131K |
| Reasoning | A | Runs well | 165.3 tok/s | 1384 ms | 131K |
| RAG | A | Runs well | 165.3 tok/s | 2129 ms | 131K |
How Granite 4.1 30B (30B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 11.7 GB | Low | A73 |
Q3_K_S | 3 | 14.7 GB | Low | A73 |
NVFP4 | 4 |
Copy-paste commands to run Granite 4.1 30B on your machine.
Run
ollama run granite4.1:30bYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | A | 28.9 tok/s | ||
| 30.5B | S |
Yes, NVIDIA H100 80GB can run Granite 4.1 30B with a A grade (Runs well). Expected decode speed: 165.3 tok/s.
Granite 4.1 30B (30B parameters) requires approximately 31.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Granite 4.1 30B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H100 80GB, Granite 4.1 30B achieves approximately 165.3 tokens per second decode speed with a time-to-first-token of 1171ms using Q4_K_M quantization.
For coding workloads, Granite 4.1 30B on NVIDIA H100 80GB receives a A grade with 165.3 tok/s and 131K context.
On NVIDIA H100 80GB, Granite 4.1 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/granite-4.1-30b-on-h100-80gb" 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 |
| A74 |
Q4_K_M | 4 | 18.3 GB | Medium | A74 |
Q5_K_M | 5 | 21.6 GB | High | A74 |
Q6_K | 6 | 24.6 GB | High | A75 |
Q8_0 | 8 | 32.1 GB | Very High | A77 |
F16Best for your GPU | 16 | 61.5 GB | Maximum | A80 |
| 425.5 tok/s |
| 122B | S | 85.5 tok/s |
| 35B | S | 357.6 tok/s |
| 35B | S | 388.9 tok/s |