32 GB VRAM (+8)1792 GB/s (+1492)
C
Raises estimated decode speed by about 208%.152 tok/s decode
Raises estimated decode speed by about 208%.
Adds memory headroom for longer context windows and future model growth.
~$1,999 MSRP
Can Granite 3.1 8B run on NVIDIA L4 24GB?
YES — Runs Great
C54Usable
○Estimated from fit model
Granite 3.1 8B needs ~10.1 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~49 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Balanced
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) — 10.1 GB, 49.4 tok/s, Runs well
10.1 GB required24.0 GB available
42% VRAM used
Fit status
Runs well
Decode
49.4 tok/s
TTFT
3919 ms
Safe context
128K
Memory
10.1 GB / 24.0 GB
Memory breakdown
Weights4.9 GB
KV Cache2.0 GB
Runtime0.9 GB
Headroom2.4 GB
See how fast it feels
See how fast it feelsGranite 3.1 8B on NVIDIA L4 24GB
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: 49.4 tok/s decode · 3.9s TTFT (warm) · 124 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 49.4 tok/s | 2138 ms | 128K |
| Coding | C | Runs well | 49.4 tok/s | 3919 ms | 128K |
| Agentic Coding | B | Runs well | 49.4 tok/s | 5700 ms | 128K |
| Reasoning | C | Runs well | 49.4 tok/s | 4632 ms | 128K |
| RAG | B | Runs well | 49.4 tok/s | 7126 ms | 128K |
Quantization options
How Granite 3.1 8B (8B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.1 GB | Low | C49 |
Q3_K_S | 3 | 3.9 GB | Low | C49 |
NVFP4 | 4 | 4.5 GB | Medium | C50 |
Q4_K_M | 4 | 4.9 GB | Medium | C50 |
Q5_K_M | 5 | 5.8 GB | High | C51 |
Q6_K | 6 | 6.6 GB | High | C51 |
Q8_0 | 8 | 8.6 GB | Very High | C52 |
F16Best for your GPU | 16 | 16.4 GB | Maximum | C54 |
Get started
Copy-paste commands to run Granite 3.1 8B on your machine.
Run
ollama run granite3.1-denseUpgrade options
Hardware that runs Granite 3.1 8B well
32 GB VRAM (+8)896 GB/s (+596)
C
Raises estimated decode speed by about 127%.112 tok/s decode
Raises estimated decode speed by about 127%.
Adds memory headroom for longer context windows and future model growth.
~$2,499 MSRP
32 GB VRAM (+8)576 GB/s (+276)
C
Raises estimated decode speed by about 127%.112 tok/s decode
Raises estimated decode speed by about 127%.
Adds memory headroom for longer context windows and future model growth.
~$4,000 MSRP