NVIDIA H200 141GB经济之选141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 210%.112 tok/s 解码
Raises estimated decode speed by about 210%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Can Granite Code 8B run on NVIDIA DGX Spark 128GB?
YES — With F16
B68Good
Estimated from fit model
Granite Code 8B needs ~32.6 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~15 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.
Granite Code 8B at Q4_K_M needs 8.0 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at F16 (32.6 GB) with maximum quality. 8 quantization levels fit.
Select quantization to explore
Q4_K_M (Medium quality) — 21.1 GB, 36.1 tok/s, Runs well
21.1 GB required108.8 GB available
19% VRAM used
Fit status
Runs well
Decode
36.1 tok/s
TTFT
5365 ms
Safe context
8K
Memory
21.1 GB / 108.8 GB
Memory breakdown
Weights4.9 GB
KV Cache2.0 GB
Runtime1.2 GB
Headroom13.1 GB
See how fast it feels
See how fast it feelsGranite Code 8B 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: 36.1 tok/s decode · 5.4s TTFT (warm) · 90 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 | 36.1 tok/s | 2927 ms | 8K |
| Coding | F | Too heavy | 6.0 tok/s | 32043 ms | 4K |
| Agentic Coding | B | Runs well | 36.1 tok/s | 7804 ms | 8K |
| Reasoning | B | Runs well | 36.1 tok/s | 6341 ms | 8K |
| RAG | B | Runs well | 36.1 tok/s | 9755 ms | 8K |
Quantization options
How Granite Code 8B (8B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | B64 |
Q3_K_S | 3 | 3.9 GB | Low | B64 |
NVFP4 | 4 | 4.5 GB | Medium | B64 |
Q4_K_M | 4 | 4.9 GB | Medium | B64 |
Q5_K_M | 5 | 5.8 GB | High | B64 |
Q6_K | 6 | 6.6 GB | High | B64 |
Q8_0 | 8 | 8.6 GB | Very High | B65 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | B65 |
Get started
Copy-paste commands to run Granite Code 8B on your machine.
Run
ollama run granite-code:8b升级选项
能流畅运行 Granite Code 8B 的硬件
NVIDIA H200 141GB经济之选NVIDIA H200 PCIe 141GB最佳性价比141 GB VRAM (+13)4800 GB/s (+4527)
A
Raises estimated decode speed by about 210%.112 tok/s 解码
Raises estimated decode speed by about 210%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
NVIDIA B200 180GBNVIDIA 升级180 GB VRAM (+52)8000 GB/s (+7727)
A
Raises estimated decode speed by about 210%.112 tok/s 解码
Raises estimated decode speed by about 210%.
Adds memory headroom for longer context windows and future model growth.
~$30,000 MSRP
Frequently asked questions
Can NVIDIA DGX Spark 128GB run Granite Code 8B?
Yes, NVIDIA DGX Spark 128GB can run Granite Code 8B at F16 quantization (Runs well). The recommended Q4_K_M requires 8.0 GB which exceeds available memory, but at F16 it needs only 32.6 GB. Expected decode speed: 15.0 tok/s.
How much VRAM does Granite Code 8B need?
Granite Code 8B (8B parameters) requires approximately 8.0 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 32.6 GB.
What is the best quantization for Granite Code 8B?
The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 32.6 GB.
What speed will Granite Code 8B run at on NVIDIA DGX Spark 128GB?
On NVIDIA DGX Spark 128GB, Granite Code 8B achieves approximately 15.0 tokens per second decode speed with a time-to-first-token of 12879ms using F16 quantization.
Can NVIDIA DGX Spark 128GB run Granite Code 8B for coding?
For coding workloads, Granite Code 8B on NVIDIA DGX Spark 128GB receives a F grade with 6.0 tok/s and 4K context.
What context window can Granite Code 8B use on NVIDIA DGX Spark 128GB?
On NVIDIA DGX Spark 128GB, Granite Code 8B can safely use up to 8K tokens of context at F16 quantization. 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 Granite Code 8B?
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/granite-code-8b-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: