NVIDIA H200 141GBコスパ重視141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 138%.98 tok/sデコード
Raises estimated decode speed by about 138%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
Can DevStral 7B run on NVIDIA DGX Spark 128GB?
YES — Runs Great
B68Good
Estimated from fit model
DevStral 7B needs ~20.5 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~41 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Balanced
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) — 20.5 GB, 41.2 tok/s, Runs well
20.5 GB required108.8 GB available
19% VRAM used
Fit status
Runs well
Decode
41.2 tok/s
TTFT
4695 ms
Safe context
8K
Memory
20.5 GB / 108.8 GB
Memory breakdown
Weights4.3 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom13.1 GB
See how fast it feels
See how fast it feelsDevStral 7B 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: 41.2 tok/s decode · 4.7s TTFT (warm) · 103 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 41.2 tok/s | 2561 ms | 8K |
| Coding | B | Runs well | 41.2 tok/s | 4695 ms | 8K |
| Agentic Coding | B | Runs well | 41.2 tok/s | 6829 ms | 8K |
| Reasoning | B | Runs well | 41.2 tok/s | 5548 ms | 8K |
| RAG | B | Runs well | 41.2 tok/s | 8536 ms | 8K |
Quantization options
How DevStral 7B (7B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | B64 |
Q3_K_S | 3 | 3.4 GB | Low | B64 |
NVFP4 | 4 | 3.9 GB | Medium | B64 |
Q4_K_M | 4 | 4.3 GB | Medium | B64 |
Q5_K_M | 5 | 5.0 GB | High | B64 |
Q6_K | 6 | 5.7 GB | High | B64 |
Q8_0 | 8 | 7.5 GB | Very High | B64 |
F16Best for your GPU | 16 | 14.3 GB | Maximum | B65 |
Get started
Copy-paste commands to run DevStral 7B on your machine.
Run
ollama run devstralアップグレードオプション
DevStral 7Bを快適に動かすハードウェア
NVIDIA H200 141GBコスパ重視NVIDIA H200 PCIe 141GBコスパ最良141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 138%.98 tok/sデコード
Raises estimated decode speed by about 138%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
NVIDIA B200 180GBNVIDIAアップグレード180 GB VRAM (+52)8000 GB/s (+7727)
A
Raises estimated decode speed by about 138%.98 tok/sデコード
Raises estimated decode speed by about 138%.
Adds memory headroom for longer context windows and future model growth.
〜$30,000 MSRP
Frequently asked questions
Can NVIDIA DGX Spark 128GB run DevStral 7B?
Yes, NVIDIA DGX Spark 128GB can run DevStral 7B with a B grade (Runs well). Expected decode speed: 41.2 tok/s.
How much VRAM does DevStral 7B need?
DevStral 7B (7B parameters) requires approximately 20.5 GB of memory with Q4_K_M quantization.
What is the best quantization for DevStral 7B?
The recommended quantization for DevStral 7B is Q4_K_M, which balances quality and memory efficiency.
What speed will DevStral 7B run at on NVIDIA DGX Spark 128GB?
On NVIDIA DGX Spark 128GB, DevStral 7B achieves approximately 41.2 tokens per second decode speed with a time-to-first-token of 4695ms using Q4_K_M quantization.
Can NVIDIA DGX Spark 128GB run DevStral 7B for coding?
For coding workloads, DevStral 7B on NVIDIA DGX Spark 128GB receives a B grade with 41.2 tok/s and 8K context.
What context window can DevStral 7B use on NVIDIA DGX Spark 128GB?
On NVIDIA DGX Spark 128GB, DevStral 7B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.
Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for DevStral 7B?
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.
Embed this result▼
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/devstral-7b-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: