Command R+ 104B needs ~128.7 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With Q8_0 quantization, expect ~2 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
2.8 tok/s
TTFT
68949 ms
Safe context
131K
Memory
80.8 GB / 108.8 GB
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
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.
Shared-memory contention still exists
The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 17.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | F | Too heavy | 2.0 tok/s | 52800 ms | 4K |
| Coding | F | Too heavy | 2.0 tok/s | 96800 ms | 4K |
| Agentic Coding | F | Too heavy | 2.0 tok/s | 140800 ms | 4K |
| Reasoning | F | Too heavy | 2.0 tok/s | 114400 ms | 4K |
| RAG | F | Too heavy | 2.0 tok/s | 176000 ms | 4K |
How Command R+ 104B (104B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 40.6 GB | Low | B63 |
Q3_K_S | 3 | 51.0 GB | Low | B65 |
NVFP4 | 4 | 58.2 GB | Medium | B65 |
Q4_K_M | 4 | 63.4 GB | Medium | B65 |
Q5_K_MBest for your GPU | 5 | 74.9 GB | High | B65 |
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-plusOpções de upgrade
NVIDIA H200 141GBOpção econômicaRaises estimated decode speed by about 2368%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA H200 PCIe 141GBMelhor custo-benefícioRaises estimated decode speed by about 2368%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA B200 180GBUpgrade NVIDIARaises estimated decode speed by about 4014%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Yes, NVIDIA DGX Spark 128GB can run Command R+ 104B at Q8_0 quantization (Very compromised (needs ~17.2 GB host RAM)). The recommended Q4_K_M requires 67.8 GB which exceeds available memory, but at Q8_0 it needs only 128.7 GB. Expected decode speed: 2.0 tok/s.
Command R+ 104B (104B parameters) requires approximately 67.8 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at Q8_0 using 128.7 GB.
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q8_0, which uses 128.7 GB.
On NVIDIA DGX Spark 128GB, Command R+ 104B achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 96800ms using Q8_0 quantization.
For coding workloads, Command R+ 104B on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.
On NVIDIA DGX Spark 128GB, Command R+ 104B can safely use up to 4K tokens of context at Q8_0 quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/command-r-plus-104b-on-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: