DeepSeek R1 671B needs ~488.6 GB but H100 NVL 188GB only has 188.0 GB. Try a smaller quantization or lighter model.
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
300.6 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
7.9 tok/s
TTFT
24465 ms
Safe context
4K
Memory
488.6 GB / 188.0 GB
Offload
60%
Usable VRAM is the main blocker for this model.
Not enough usable memory
The model needs 488.6 GB, but this setup only exposes 188.0 GB of usable VRAM.
Add more VRAM headroom
The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 8.8 tok/s | 12029 ms | 4K |
| Coding | F | Too heavy | 7.9 tok/s | 24465 ms | 4K |
| Agentic Coding | F | Too heavy | 6.7 tok/s | 41852 ms | 4K |
| Reasoning | F | Too heavy | 7.9 tok/s | 28913 ms | 4K |
| RAG | F | Too heavy | 6.7 tok/s | 52315 ms | 4K |
How DeepSeek R1 671B (671B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 261.7 GB | Low | F0 |
Q3_K_S | 3 | 328.8 GB | Low | F0 |
NVFP4 | 4 |
No, DeepSeek R1 671B requires more memory than H100 NVL 188GB provides.
DeepSeek R1 671B (671B parameters) requires approximately 488.6 GB of memory with Q4_K_M quantization.
The recommended quantization for DeepSeek R1 671B is Q4_K_M, which balances quality and memory efficiency.
On H100 NVL 188GB, DeepSeek R1 671B achieves approximately 7.9 tokens per second decode speed with a time-to-first-token of 24465ms using Q4_K_M quantization.
For coding workloads, DeepSeek R1 671B on H100 NVL 188GB receives a F grade with 7.9 tok/s and 4K context.
On H100 NVL 188GB, DeepSeek R1 671B can safely use up to 4K 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/deepseek-r1-671b-on-h100-nvl-188gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview:
| Medium |
| F0 |
Q4_K_M | 4 | 409.3 GB | Medium | F0 |
Q5_K_M | 5 | 483.1 GB | High | F0 |
Q6_K | 6 | 550.2 GB | High | F0 |
Q8_0 | 8 | 718.0 GB | Very High | F0 |
F16 | 16 | 1375.6 GB | Maximum | F0 |
Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.