Can InternLM 20B run on MacBook Air M2 16GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

InternLM 20B needs ~35.3 GB but MacBook Air M2 16GB only has 11.5 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: Very lowStack: StandardBottleneck: Memory capacity

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) — 35.3 GB, exceeds 11.5 GB available

35.3 GB required11.5 GB available

307% VRAM needed

23.8 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.1 tok/s

TTFT

93442 ms

Safe context

Memory

35.3 GB / 11.5 GB

Offload

70%

Memory breakdown

Weights14.4 GB

KV Cache18.3 GB

Runtime0.9 GB

Headroom1.7 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsInternLM 20B on MacBook Air M2 16GB
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: 2.1 tok/s decode · 93.4s TTFT (warm) · 5 tok/s prefill

What limits this setup

Usable shared or unified memory is the main blocker for this model.

Not enough usable memory

The model needs 35.3 GB, but this setup only exposes 11.5 GB of usable shared or unified memory.

Best improvement path

Move to a larger memory pool

A larger unified-memory SKU or a discrete high-bandwidth GPU is the cleanest way to make this model practical.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	2.1 tok/s	50968 ms	4K
Coding	F	Too heavy	2.1 tok/s	93442 ms	4K
Agentic Coding	F	Too heavy	2.1 tok/s	135916 ms	4K
Reasoning	F	Too heavy	2.1 tok/s	110431 ms	4K
RAG	F	Too heavy	2.1 tok/s	169894 ms	4K

Quantization options

How InternLM 20B (20B params) fits at each quantization level on MacBook Air M2 16GB (11.5 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	7.8 GB	Low	B60
Q3_K_S	3	9.8 GB	Low	F0
NVFP4	4	11.2 GB	Medium	F0
Q4_K_M	4	12.2 GB	Medium	F0
Q5_K_M	5	14.4 GB	High	F0
Q6_K	6	16.4 GB	High	F0
Q8_0	8	21.4 GB	Very High	F0
F16	16	41.0 GB	Maximum	F0

Opciones de mejora

Hardware que ejecuta bien InternLM 20B

Mac mini M4 64GBOpción económica

64 GB Unified (+48)120 GB/s (+20)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.8 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$1,099 MSRP

MacBook Pro M4 Pro 64GBMejor relación calidad-precio

64 GB Unified (+48)273 GB/s (+173)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.19.4 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$1,599 MSRP

MacBook Pro M4 Max 96GBMejora Apple

96 GB Unified (+80)546 GB/s (+446)

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.30.7 tok/s decodificación

Hace que el modelo quepa en el acelerador en lugar de seguir fuera de alcance.

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

~$2,499 MSRP

Frequently asked questions

Can MacBook Air M2 16GB run InternLM 20B?

No, InternLM 20B requires more memory than MacBook Air M2 16GB provides.

How much VRAM does InternLM 20B need?

InternLM 20B (20B parameters) requires approximately 35.3 GB of memory with Q5_K_M quantization.

What is the best quantization for InternLM 20B?

The recommended quantization for InternLM 20B is Q5_K_M, which balances quality and memory efficiency.

What speed will InternLM 20B run at on MacBook Air M2 16GB?

On MacBook Air M2 16GB, InternLM 20B achieves approximately 2.1 tokens per second decode speed with a time-to-first-token of 93442ms using Q5_K_M quantization.

Can MacBook Air M2 16GB run InternLM 20B for coding?

For coding workloads, InternLM 20B on MacBook Air M2 16GB receives a F grade with 2.1 tok/s and 4K context.

What context window can InternLM 20B use on MacBook Air M2 16GB?

On MacBook Air M2 16GB, InternLM 20B can safely use up to 4K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

What should I upgrade first if InternLM 20B feels slow on MacBook Air M2 16GB?

Move to a larger memory pool. A larger unified-memory SKU or a discrete high-bandwidth GPU is the cleanest way to make this model practical.

Is unified memory on MacBook Air M2 16GB as fast as VRAM for InternLM 20B?

Not always. MacBook Air M2 16GB 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 MacBook Air M2 16GB See all hardware for InternLM 20B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/internlm-20b-on-m2-air-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: