Can StarCoder2 15B run on Mac mini M4 32GB?

YES — Runs Great

C49Usable

Estimated — low-sample bucket· few comparable runs

StarCoder2 15B needs ~15.3 GB VRAM. Mac mini M4 32GB has 23.0 GB. With Q4_K_M quantization, expect ~9 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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

Q4_K_M (Medium quality) — 15.3 GB, 8.7 tok/s, Runs well

15.3 GB required23.0 GB available

67% VRAM used

Fit status

Runs well

Decode

8.7 tok/s

TTFT

22189 ms

Safe context

87K

Memory

15.3 GB / 23.0 GB

Memory breakdown

Weights9.2 GB

KV Cache1.8 GB

Runtime0.9 GB

Headroom3.5 GB

See how fast it feels

See how fast it feelsStarCoder2 15B on Mac mini M4 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: 8.7 tok/s decode · 22.2s TTFT (warm) · 22 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	8.7 tok/s	12103 ms	87K
Coding	C	Runs well	8.7 tok/s	22189 ms	87K
Agentic Coding	C	Runs well	8.7 tok/s	32275 ms	87K
Reasoning	C	Runs well	8.7 tok/s	26224 ms	87K
RAG	C	Runs well	8.7 tok/s	40344 ms	87K

Inference speed

StarCoder2 15B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for StarCoder2 15B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~131 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	131.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	83.7	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	75.5	Fits
RTX 3090 24GB	24 GB	Q4_K_M	71.6	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	68.3	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	60.9	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	50.7	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	48.1	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	34.7	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	34.7	Fits
RTX 4070 12GB	12 GB	Q4_K_M	26.7	Heavy offload
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	26.2	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	24.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	21.2	Fits
RTX 3060 12GB	12 GB	Q4_K_M	15.7	Heavy offload
RTX 4060 8GB	8 GB	Q4_K_M	5.9	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Mac mini M4 32GB (23.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C46
Q3_K_S	3	7.4 GB	Low	C47
NVFP4	4	8.4 GB	Medium	C48
Q4_K_M	4	9.2 GB	Medium	C48
Q5_K_M	5	10.8 GB	High	C50
Q6_K	6	12.3 GB	High	C50
Q8_0Best for your GPU	8	16.1 GB	Very High	C50
F16	16	30.7 GB	Maximum	F0

Get started

Copy-paste commands to run StarCoder2 15B on your machine.

Run

lms load hf-second-state--starcoder2-15b-gguf && lms server start

Upgrade options

Hardware that runs StarCoder2 15B well

MacBook Pro M4 Max 36GBBudget pick

36 GB Unified (+4)410 GB/s (+290)

Raises estimated decode speed by about 240%.29.6 tok/s decode

Raises estimated decode speed by about 240%.

~$2,499 MSRP

MacBook Pro M4 Max 48GBBest value

48 GB Unified (+16)546 GB/s (+426)

Raises estimated decode speed by about 299%.34.7 tok/s decode

Raises estimated decode speed by about 299%.

Adds memory headroom for longer context windows and future model growth.

~$2,499 MSRP

Frequently asked questions

Can Mac mini M4 32GB run StarCoder2 15B?

Yes, Mac mini M4 32GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 8.7 tok/s.

How much VRAM does StarCoder2 15B need?

StarCoder2 15B (15B parameters) requires approximately 15.3 GB of memory with Q4_K_M quantization.

What is the best quantization for StarCoder2 15B?

The recommended quantization for StarCoder2 15B is Q4_K_M, which balances quality and memory efficiency.

What speed will StarCoder2 15B run at on Mac mini M4 32GB?

On Mac mini M4 32GB, StarCoder2 15B achieves approximately 8.7 tokens per second decode speed with a time-to-first-token of 22189ms using Q4_K_M quantization.

Can Mac mini M4 32GB run StarCoder2 15B for coding?

For coding workloads, StarCoder2 15B on Mac mini M4 32GB receives a C grade with 8.7 tok/s and 87K context.

What context window can StarCoder2 15B use on Mac mini M4 32GB?

On Mac mini M4 32GB, StarCoder2 15B can safely use up to 87K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on Mac mini M4 32GB as fast as VRAM for StarCoder2 15B?

Not always. Mac mini M4 32GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for Mac mini M4 32GB See all hardware for StarCoder2 15B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-second-state--starcoder2-15b-gguf-on-m4-mini-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

8.7 tok/s

12103 ms

87K

Coding

Runs well

8.7 tok/s

22189 ms

87K

Agentic Coding

Runs well

8.7 tok/s

32275 ms

87K

Reasoning

Runs well

8.7 tok/s

26224 ms

87K

RAG

Runs well

8.7 tok/s

40344 ms

87K

StarCoder2 15B inference speed — tokens per second by GPU & Mac

GPU / Mac

Memory

Quant

Speed (tok/s)

Fits?

RTX 5090 32GB

32 GB

Q4_K_M

131.2

Fits

RTX 4090 24GB

24 GB

Q4_K_M

83.7

Fits

RX 7900 XTX 24GB

24 GB

Q4_K_M

75.5

Fits

RTX 3090 24GB

24 GB

Q4_K_M

71.6

Fits

RTX 4080 Super 16GB

16 GB

Q4_K_M

68.3

Tight

Mac Studio M3 Ultra 256GB

256 GB

Q4_K_M

60.9

Fits

Mac Studio M2 Ultra 128GB

128 GB

Q4_K_M

50.7

Fits

Mac Studio M1 Ultra 128GB

128 GB

Q4_K_M

48.1

Fits

MacBook Pro M4 Max 128GB

128 GB

Q4_K_M

34.7

Fits

MacBook Pro M4 Max 64GB

64 GB

Q4_K_M

34.7

Fits

RTX 4070 12GB

12 GB

Q4_K_M

26.7

Heavy offload

MacBook Pro M3 Max 64GB

64 GB

Q4_K_M

26.2

Fits

MacBook Pro M1 Max 64GB

64 GB

Q4_K_M

24.0

Fits

MacBook Pro M4 Pro 48GB

48 GB

Q4_K_M

21.2

Fits

RTX 3060 12GB

12 GB

Q4_K_M

15.7

Heavy offload

RTX 4060 8GB

8 GB

Q4_K_M

5.9

Too big

Quantization options

How StarCoder2 15B (15B params) fits at each quantization level on Mac mini M4 32GB (23.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C46
Q3_K_S	3	7.4 GB	Low	C47
NVFP4	4	8.4 GB	Medium	C48
Q4_K_M	4	9.2 GB	Medium	C48
Q5_K_M	5	10.8 GB	High	C50
Q6_K	6	12.3 GB	High	C50
Q8_0Best for your GPU	8	16.1 GB	Very High	C50
F16	16	30.7 GB	Maximum	F0

Frequently asked questions

Can Mac mini M4 32GB run StarCoder2 15B?

Yes, Mac mini M4 32GB can run StarCoder2 15B with a C grade (Runs well). Expected decode speed: 8.7 tok/s.

How much VRAM does StarCoder2 15B need?

StarCoder2 15B (15B parameters) requires approximately 15.3 GB of memory with Q4_K_M quantization.

What is the best quantization for StarCoder2 15B?

The recommended quantization for StarCoder2 15B is Q4_K_M, which balances quality and memory efficiency.

What speed will StarCoder2 15B run at on Mac mini M4 32GB?

On Mac mini M4 32GB, StarCoder2 15B achieves approximately 8.7 tokens per second decode speed with a time-to-first-token of 22189ms using Q4_K_M quantization.

Can Mac mini M4 32GB run StarCoder2 15B for coding?

For coding workloads, StarCoder2 15B on Mac mini M4 32GB receives a C grade with 8.7 tok/s and 87K context.

What context window can StarCoder2 15B use on Mac mini M4 32GB?

On Mac mini M4 32GB, StarCoder2 15B can safely use up to 87K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on Mac mini M4 32GB as fast as VRAM for StarCoder2 15B?