Can InternLM 20B run on Mac mini M4 64GB?

YES — Tight Fit

C53Usable

▲Estimated — low-sample bucket· few comparable runs

InternLM 20B needs ~40.5 GB VRAM. Mac mini M4 64GB has 46.1 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) — 40.5 GB, 8.0 tok/s, Tight fit

40.5 GB required46.1 GB available

88% VRAM used

Fit status

Tight fit

Decode

8.0 tok/s

TTFT

24334 ms

Safe context

Memory

40.5 GB / 46.1 GB

Memory breakdown

Weights14.4 GB

KV Cache18.3 GB

Runtime0.9 GB

Headroom6.9 GB

See how fast it feels

See how fast it feelsInternLM 20B on Mac mini M4 64GB
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: 8.0 tok/s decode · 24.3s TTFT (warm) · 20 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	B	Runs well	6.1 tok/s	17255 ms	8K
Coding	C	Tight fit	6.1 tok/s	31634 ms	8K
Agentic Coding	F	Too heavy	4.3 tok/s	65202 ms	8K
Reasoning	C	Tight fit	6.1 tok/s	37386 ms	8K
RAG	F	Too heavy	4.3 tok/s	81503 ms	8K

Quantization options

How InternLM 20B (20B params) fits at each quantization level on Mac mini M4 64GB (46.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.8 GB	Low	C50
Q3_K_S	3	9.8 GB	Low	C51
NVFP4	4

Get started

Copy-paste commands to run InternLM 20B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "internlm/internlm2_5-20b-chat" \
 --hf-file "internlm2_5-20b-chat-Q5_K_M.gguf" \
 -c 4096 -ngl 99

Upgrade options