Can StarCoder2 15B run on Mac mini M2 24GB?

YES — Tight Fit

C47Usable

○Estimated from fit model

StarCoder2 15B needs ~15.5 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q5_K_M quantization, expect ~6 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

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.

Capabilities:

Select quantization to explore

Q5_K_M (High quality) — 15.5 GB, 6.7 tok/s, Tight fit

15.5 GB required17.3 GB available

90% VRAM used

Fit status

Tight fit

Decode

6.7 tok/s

TTFT

28889 ms

Safe context

16K

Memory

15.5 GB / 17.3 GB

Memory breakdown

Weights10.8 GB

KV Cache1.2 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on Mac mini M2 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: 6.7 tok/s decode · 28.9s TTFT (warm) · 17 tok/s prefill

What limits this setup

The model fits in shared memory, but shared-memory bandwidth is now the real limiter.

Fit does not mean dedicated-VRAM speed

Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.

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

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Tight fit	6.1 tok/s	17202 ms	16K
Coding	C	Tight fit	6.1 tok/s	31537 ms	16K
Agentic Coding	C	Runs with offload	6.1 tok/s	45871 ms	16K
Reasoning	C	Tight fit	6.1 tok/s	37271 ms	16K
RAG	C	Runs with offload	6.1 tok/s	57339 ms	16K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Mac mini M2 24GB (17.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C50
Q3_K_S	3	7.4 GB	Low	C52
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 99

Upgrade options