141 GB VRAM (+13)4800 GB/s (+4527)
S
Raises estimated decode speed by about 2400%.65 tok/s decode
Raises estimated decode speed by about 2400%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Can Command A 111B run on NVIDIA DGX Spark 128GB?
YES — With Q6_K
A83Great
○Estimated from fit model
Command A 111B needs ~108.9 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With Q6_K quantization, expect ~2 tok/s.
Runtime: llama.cppCapacity: OffloadBandwidth: 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.
Command A 111B at Q4_K_M needs 72.5 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at Q6_K (108.9 GB) with high quality. 6 quantization levels fit.
Select quantization to explore
Q4_K_M (Medium quality) — 85.6 GB, 2.6 tok/s, Runs well
85.6 GB required108.8 GB available
79% VRAM used
Fit status
Runs well
Decode
2.6 tok/s
TTFT
73308 ms
Safe context
111K
Memory
85.6 GB / 108.8 GB
Memory breakdown
Weights67.7 GB
KV Cache3.9 GB
Runtime0.9 GB
Headroom13.1 GB
See how fast it feels
See how fast it feelsCommand A 111B on NVIDIA DGX Spark 128GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:
def quicksort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]
The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
"""Sort a list using the quicksort algorithm.
Args:
arr: List of integers to sort.
Returns:
A new sorted list.
"""
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
left = [x for x in arr if x < pivot]
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)
Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 2.6 tok/s decode · 73.3s 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.
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.
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.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Performance by workload
| 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 |
Quantization options
How Command A 111B (111B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 43.3 GB | Low | S87 |
Q3_K_S | 3 | 54.4 GB | Low | S88 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Command A 111B on your machine.
Run
ollama run command-aUpgrade options
Hardware that runs Command A 111B well
141 GB VRAM (+13)4800 GB/s (+4527)
S
Raises estimated decode speed by about 2400%.65 tok/s decode
Raises estimated decode speed by about 2400%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
180 GB VRAM (+52)8000 GB/s (+7727)
S
Raises estimated decode speed by about 4065%.108.3 tok/s decode
Raises estimated decode speed by about 4065%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP