672 GB/s (+572)
B
Raises estimated decode speed by about 61%.57 tok/s decode
Raises estimated decode speed by about 61%.
~$549 MSRP
Can Granite Code 3B run on MacBook Air M2 16GB?
YES — Runs Great
B68Good
○Estimated from fit model
Granite Code 3B needs ~6.9 GB VRAM. MacBook Air M2 16GB has 11.5 GB. With Q4_K_M quantization, expect ~36 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: Very 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) — 6.9 GB, 35.5 tok/s, Runs well
6.9 GB required11.5 GB available
60% VRAM used
Fit status
Runs well
Decode
35.5 tok/s
TTFT
5451 ms
Safe context
8K
Memory
6.9 GB / 11.5 GB
Memory breakdown
Weights1.8 GB
KV Cache2.5 GB
Runtime0.9 GB
Headroom1.7 GB
See how fast it feels
See how fast it feelsGranite Code 3B on MacBook Air M2 16GB
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: 35.5 tok/s decode · 5.5s TTFT (warm) · 89 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 | 35.5 tok/s | 2973 ms | 8K |
| Coding | B | Runs well | 35.5 tok/s | 5451 ms | 8K |
| Agentic Coding | B | Runs well | 35.5 tok/s | 7928 ms | 8K |
| Reasoning | B | Runs well | 35.5 tok/s | 6442 ms | 8K |
| RAG | B | Runs well | 35.5 tok/s | 9910 ms | 8K |
Quantization options
How Granite Code 3B (3B params) fits at each quantization level on MacBook Air M2 16GB (11.5 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 1.2 GB | Low | B64 |
Q3_K_S | 3 | 1.5 GB | Low | B64 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Granite Code 3B on your machine.
Run
ollama run granite-code:3bUpgrade options