RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick96 GB VRAM (+16)
A
This setup is broadly balanced for this model.25.8 tok/s decode
~$9,999 MSRP
Command R+ 104B needs ~75.8 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~48 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
Tight fit
Decode
48.2 tok/s
TTFT
4013 ms
Safe context
36K
Memory
75.8 GB / 80.0 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 | B | Tight fit | 48.2 tok/s | 2189 ms | 36K |
| Coding | B | Tight fit | 48.2 tok/s | 4013 ms | 36K |
| Agentic Coding | B | Runs with offload | 48.2 tok/s | 5838 ms | 36K |
| Reasoning | B | Tight fit | 48.2 tok/s | 4743 ms | 36K |
| RAG | B | Runs with offload | 48.2 tok/s | 7297 ms | 36K |
How Command R+ 104B (104B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B65 |
Q3_K_S | 3 | 51.0 GB | Low | B65 |
NVFP4 | 4 | 58.2 GB | Medium | B65 |
Q4_K_MBest for your GPU | 4 | 63.4 GB | Medium | B65 |
Q5_K_M | 5 | 74.9 GB | High | F0 |
Q6_K | 6 | 85.3 GB | High | F0 |
Q8_0 | 8 | 111.3 GB | Very High | F0 |
F16 | 16 | 213.2 GB | Maximum | F0 |
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusUpgrade options
RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick~$9,999 MSRP
RTX PRO 6000 Blackwell Server Edition 96GBBest value~$9,999 MSRP
NVIDIA H20 96GBNVIDIA upgrade~$12,000 MSRP
Yes, NVIDIA H100 80GB can run Command R+ 104B with a B grade (Tight fit). Expected decode speed: 48.2 tok/s.
Command R+ 104B (104B parameters) requires approximately 75.8 GB of memory with Q4_K_M quantization.
The recommended quantization for Command R+ 104B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA H100 80GB, Command R+ 104B achieves approximately 48.2 tokens per second decode speed with a time-to-first-token of 4013ms using Q4_K_M quantization.
For coding workloads, Command R+ 104B on NVIDIA H100 80GB receives a B grade with 48.2 tok/s and 36K context.
On NVIDIA H100 80GB, Command R+ 104B can safely use up to 36K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/command-r-plus-104b-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: