Can InternLM 20B run on MacBook Pro M1 Max 64GB?

YES — Tight Fit

B56Good

○Estimated from fit model

InternLM 20B needs ~40.5 GB VRAM. MacBook Pro M1 Max 64GB has 46.1 GB. With Q5_K_M quantization, expect ~16 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: LowStack: 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) — 40.5 GB, 15.6 tok/s, Tight fit

40.5 GB required46.1 GB available

88% VRAM used

Fit status

Tight fit

Decode

15.6 tok/s

TTFT

12424 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 MacBook Pro M1 Max 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: 15.6 tok/s decode · 12.4s TTFT (warm) · 39 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	B	Runs well	15.6 tok/s	6776 ms	8K
Coding	B	Tight fit	15.6 tok/s	12424 ms	8K
Agentic Coding	F	Too heavy	11.0 tok/s	25607 ms	8K
Reasoning	B	Tight fit	15.6 tok/s	14682 ms	8K
RAG	F	Too heavy	11.0 tok/s	32008 ms	8K

Quantization options

How InternLM 20B (20B params) fits at each quantization level on MacBook Pro M1 Max 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	11.2 GB	Medium	C51
Q4_K_M	4	12.2 GB	Medium	C52
Q5_K_M	5	14.4 GB	High	C52
Q6_K	6	16.4 GB	High	C53
Q8_0Best for your GPU	8	21.4 GB	Very High	C55
F16	16	41.0 GB	Maximum	F0

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