Can internlm JanusCoder 14B run on Mac mini M2 24GB?

YES — Runs Great

C49Usable

○Estimated from fit model

internlm JanusCoder 14B needs ~13.7 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q4_K_M quantization, expect ~8 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) — 13.7 GB, 7.6 tok/s, Runs well

13.7 GB required17.3 GB available

79% VRAM used

Fit status

Runs well

Decode

7.6 tok/s

TTFT

25436 ms

Safe context

51K

Memory

13.7 GB / 17.3 GB

Memory breakdown

Weights8.5 GB

KV Cache1.6 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsinternlm JanusCoder 14B 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: 7.6 tok/s decode · 25.4s TTFT (warm) · 19 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	Runs well	7.6 tok/s	13874 ms	51K
Coding	C	Runs well	7.6 tok/s	25436 ms	51K
Agentic Coding	C	Tight fit	7.6 tok/s	36998 ms	51K
Reasoning	C	Runs well	7.6 tok/s	30061 ms	51K
RAG	C	Tight fit	7.6 tok/s	46247 ms	51K