Makes the model fit on the accelerator instead of staying completely out of reach.
Adds memory headroom for longer context windows and future model growth.
~$6,500 MSRP
Command R+ 104B needs ~49.7 GB VRAM. RTX 6000 Ada 48GB has 48.0 GB. With Q2_K quantization, expect ~13 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
24.6 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
4.2 tok/s
TTFT
45648 ms
Safe context
4K
Memory
72.6 GB / 48.0 GB
Offload
30%
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 | F | Too heavy | 4.1 tok/s | 25753 ms | 4K |
| Coding | F | Too heavy | 3.9 tok/s | 49642 ms | 4K |
| Agentic Coding | F | Too heavy | 3.5 tok/s | 79554 ms | 4K |
| Reasoning | F | Too heavy | 3.9 tok/s | 58668 ms | 4K |
| RAG | F | Too heavy | 3.5 tok/s | 99442 ms | 4K |
How Command R+ 104B (104B params) fits at each quantization level on RTX 6000 Ada 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | F0 |
Q3_K_S | 3 | 51.0 GB | Low | F0 |
NVFP4 | 4 |
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusUpgrade options
Makes the model fit on the accelerator instead of staying completely out of reach.
Adds memory headroom for longer context windows and future model growth.
~$6,500 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$9,999 MSRP
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$9,999 MSRP
Yes, RTX 6000 Ada 48GB can run Command R+ 104B at Q2_K quantization (Runs with offload (needs ~1.4 GB host RAM)). The recommended Q4_K_M requires 72.6 GB which exceeds available memory, but at Q2_K it needs only 49.7 GB. Expected decode speed: 12.5 tok/s.
Command R+ 104B (104B parameters) requires approximately 72.6 GB at Q4_K_M quantization. On RTX 6000 Ada 48GB, it fits at Q2_K using 49.7 GB.
The recommended quantization is Q4_K_M, but on RTX 6000 Ada 48GB the best fitting quantization is Q2_K, which uses 49.7 GB.
On RTX 6000 Ada 48GB, Command R+ 104B achieves approximately 12.5 tokens per second decode speed with a time-to-first-token of 15468ms using Q2_K quantization.
For coding workloads, Command R+ 104B on RTX 6000 Ada 48GB receives a F grade with 3.9 tok/s and 4K context.
On RTX 6000 Ada 48GB, Command R+ 104B can safely use up to 8K tokens of context at Q2_K quantization. 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/command-r-plus-104b-on-rtx-6000-ada-48gb" 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 | 63.4 GB | Medium | F0 |
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 |
Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.