RX 7900 XTX 24GBBudget pick
960 GB/s (+560)
B
Raises estimated decode speed by about 198%.71.3 tok/s decode
Raises estimated decode speed by about 198%.
~$999 MSRP
Can StarCoder2 15B run on MacBook Pro M2 Max 32GB?
YES — Runs Great
C54Usable
○Estimated from fit model
StarCoder2 15B needs ~16.4 GB VRAM. MacBook Pro M2 Max 32GB has 23.0 GB. With Q5_K_M quantization, expect ~22 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
Q5_K_M (High quality) — 16.4 GB, 23.9 tok/s, Runs well
16.4 GB required23.0 GB available
71% VRAM used
Fit status
Runs well
Decode
23.9 tok/s
TTFT
8094 ms
Safe context
16K
Memory
16.4 GB / 23.0 GB
Memory breakdown
Weights10.8 GB
KV Cache1.2 GB
Runtime0.9 GB
Headroom3.5 GB
See how fast it feels
See how fast it feelsStarCoder2 15B on MacBook Pro M2 Max 32GB
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: 23.9 tok/s decode · 8.1s TTFT (warm) · 60 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 | C | Runs well | 21.9 tok/s | 4819 ms | 16K |
| Coding | C | Runs well | 21.9 tok/s | 8836 ms | 16K |
| Agentic Coding | C | Runs well | 21.9 tok/s | 12852 ms | 16K |
| Reasoning | C | Runs well | 21.9 tok/s | 10442 ms | 16K |
| RAG | C | Runs well | 21.9 tok/s | 16065 ms | 16K |
Quantization options
How StarCoder2 15B (15B params) fits at each quantization level on MacBook Pro M2 Max 32GB (23.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C48 |
Q3_K_S | 3 | 7.4 GB | Low | C49 |
NVFP4 | 4 |
Get started
Copy-paste commands to run StarCoder2 15B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "bigcode/starcoder2-15b" \
--hf-file "starcoder2-15b-Q5_K_M.gguf" \
-c 4096 -ngl 99Upgrade options
