141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 2368%.69.1 tok/s decode
Raises estimated decode speed by about 2368%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Can Command R+ 104B run on NVIDIA DGX Spark 128GB?
YES — Runs Great
B64Good
○Estimated from fit model
Command R+ 104B needs ~80.8 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~3 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Memory bandwidth
Share:
Operating mode
Choose the run profile you care about
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
Q4_K_M (Medium quality) — 80.8 GB, 2.8 tok/s, Runs well
80.8 GB required108.8 GB available
74% VRAM used
Fit status
Runs well
Decode
2.8 tok/s
TTFT
68949 ms
Safe context
131K
Memory
80.8 GB / 108.8 GB
Memory breakdown
Weights63.4 GB
KV Cache3.4 GB
Runtime0.9 GB
Headroom13.1 GB
See how fast it feels
See how fast it feelsCommand R+ 104B on NVIDIA DGX Spark 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 2.8 tok/s decode · 68.9s TTFT (warm) · 7 tok/s prefill
What limits this setup
The model fits in shared memory, but shared-memory bandwidth is now the real limiter.
Fit does not mean dedicated-VRAM speed
Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.
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.
Best improvement path
Prioritize bandwidth, not only capacity
If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 2.8 tok/s | 37608 ms | 131K |
| Coding | B | Runs well | 2.8 tok/s | 68949 ms | 131K |
| Agentic Coding | B | Runs well | 2.8 tok/s | 100289 ms | 131K |
| Reasoning | B | Runs well | 2.8 tok/s | 81485 ms | 131K |
| RAG | B | Runs well | 2.8 tok/s | 125361 ms | 131K |
Quantization options
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 |
Get started
Copy-paste commands to run Command R+ 104B on your machine.
Run
ollama run command-r-plusUpgrade options
Hardware that runs Command R+ 104B well
141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 2368%.69.1 tok/s decode
Raises estimated decode speed by about 2368%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
180 GB VRAM (+52)8000 GB/s (+7727)
B
Raises estimated decode speed by about 4014%.115.2 tok/s decode
Raises estimated decode speed by about 4014%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP