Can StarCoder2 15B run on Mac Studio M1 Ultra 128GB?

YES — Runs Great

C47Usable

○Estimated from fit model

StarCoder2 15B needs ~26.7 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q5_K_M quantization, expect ~45 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

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) — 26.7 GB, 45.4 tok/s, Runs well

26.7 GB required92.2 GB available

29% VRAM used

Fit status

Runs well

Decode

45.4 tok/s

TTFT

4268 ms

Safe context

16K

Memory

26.7 GB / 92.2 GB

Memory breakdown

Weights10.8 GB

KV Cache1.2 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on Mac Studio M1 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: 45.4 tok/s decode · 4.3s TTFT (warm) · 113 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	45.4 tok/s	2328 ms	16K
Coding	C	Runs well	45.4 tok/s	4268 ms	16K
Agentic Coding	C	Runs well	45.4 tok/s	6207 ms	16K
Reasoning	C	Runs well	45.4 tok/s	5044 ms	16K
RAG	C	Runs well	45.4 tok/s	7759 ms	16K

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C41
Q3_K_S	3	7.4 GB	Low	C41
NVFP4	4	8.4 GB	Medium	C41
Q4_K_M	4	9.2 GB	Medium	C41
Q5_K_M	5	10.8 GB	High	C41
Q6_K	6	12.3 GB	High	C41
Q8_0	8	16.1 GB	Very High	C42
F16Best for your GPU	16	30.7 GB	Maximum	C44

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

Hardware that runs StarCoder2 15B well

👁 NVIDIA
RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick

1792 GB/s (+992)

Raises estimated decode speed by about 242%.155.2 tok/s decode

Raises estimated decode speed by about 242%.

~$9,999 MSRP

👁 NVIDIA
RTX PRO 6000 Blackwell Server Edition 96GBBest value

1597 GB/s (+797)

Raises estimated decode speed by about 205%.138.3 tok/s decode

Raises estimated decode speed by about 205%.