Gemma 4 31B needs ~48.7 GB VRAM. NVIDIA H200 PCIe 141GB has 141.0 GB. With Q4_K_M quantization, expect ~215 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
226.1 tok/s
TTFT
856 ms
Safe context
117K
Memory
48.7 GB / 141.0 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 | 226.1 tok/s | 467 ms | 117K |
| Coding | S | Runs well | 215.3 tok/s | 899 ms | 117K |
| Agentic Coding | S | Runs well | 226.1 tok/s | 1246 ms | 117K |
| Reasoning | S | Runs well | 226.1 tok/s | 1012 ms | 117K |
| RAG | S | Runs well | 226.1 tok/s | 1557 ms | 117K |
How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on NVIDIA H200 PCIe 141GB (141.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 12.0 GB | Low | A75 |
Q3_K_S | 3 | 15.0 GB | Low | A75 |
NVFP4 | 4 |
Copy-paste commands to run Gemma 4 31B on your machine.
Run
ollama run gemma4:31bYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
| 123B | S | 58.4 tok/s | ||
| 122B | S |
Yes, NVIDIA H200 PCIe 141GB can run Gemma 4 31B with a S grade (Runs well). Expected decode speed: 215.3 tok/s.
Gemma 4 31B (30.700000762939453B parameters) requires approximately 48.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Gemma 4 31B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H200 PCIe 141GB, Gemma 4 31B achieves approximately 215.3 tokens per second decode speed with a time-to-first-token of 899ms using Q4_K_M quantization.
For coding workloads, Gemma 4 31B on NVIDIA H200 PCIe 141GB receives a S grade with 215.3 tok/s and 117K context.
On NVIDIA H200 PCIe 141GB, Gemma 4 31B can safely use up to 117K tokens of context. The model's official context limit is 256K, 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/gemma-4-31b-on-h200-pcie-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
17.2 GB |
| Medium |
| A75 |
Q4_K_M | 4 | 18.7 GB | Medium | A75 |
Q5_K_M | 5 | 22.1 GB | High | A76 |
Q6_K | 6 | 25.2 GB | High | A76 |
Q8_0 | 8 | 32.8 GB | Very High | A77 |
F16Best for your GPU | 16 | 62.9 GB | Maximum | A82 |
| 162.1 tok/s |
| 35B | S | 512.4 tok/s |
| 35B | S | 557.2 tok/s |
| 32B | S | 224.6 tok/s |