1792 GB/s (+992)
B
Raises estimated decode speed by about 224%.190.4 tok/s decode
Raises estimated decode speed by about 224%.
~$9,999 MSRP
Can Qwen 2.5 Coder 14B run on Mac Studio M2 Ultra 128GB?
YES — Runs Great
B61Good
○Estimated from fit model
Qwen 2.5 Coder 14B needs ~26.2 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~59 tok/s.
Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 26.2 GB, 58.7 tok/s, Runs well
26.2 GB required92.2 GB available
28% VRAM used
Fit status
Runs well
Decode
58.7 tok/s
TTFT
3299 ms
Safe context
131K
Memory
26.2 GB / 92.2 GB
Memory breakdown
Weights8.5 GB
KV Cache2.9 GB
Runtime0.9 GB
Headroom13.8 GB
See how fast it feels
See how fast it feelsQwen 2.5 Coder 14B on Mac Studio M2 Ultra 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: 58.7 tok/s decode · 3.3s TTFT (warm) · 147 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 | 58.7 tok/s | 1800 ms | 131K |
| Coding | B | Runs well | 58.7 tok/s | 3299 ms | 131K |
| Agentic Coding | B | Runs well | 58.7 tok/s | 4799 ms | 131K |
| Reasoning | B | Runs well | 58.7 tok/s | 3899 ms | 131K |
| RAG | B | Runs well | 58.7 tok/s | 5999 ms | 131K |
Quantization options
How Qwen 2.5 Coder 14B (14B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C54 |
Q3_K_S | 3 | 6.9 GB | Low | C54 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Qwen 2.5 Coder 14B on your machine.
Run
ollama run qwen2.5-coder:14bUpgrade options