Can Codestral Mamba 7B run on MacBook Air M2 16GB?

YES — Runs Great

A75Great

○Estimated from fit model

Codestral Mamba 7B needs ~7.4 GB VRAM. MacBook Air M2 16GB has 11.5 GB. With Q4_K_M quantization, expect ~18 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) — 7.4 GB, 17.5 tok/s, Runs well

7.4 GB required11.5 GB available

64% VRAM used

Fit status

Runs well

Decode

17.5 tok/s

TTFT

11059 ms

Safe context

151K

Memory

7.4 GB / 11.5 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom1.7 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B 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: 17.5 tok/s decode · 11.1s TTFT (warm) · 44 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	A	Runs well	17.5 tok/s	6032 ms	151K
Coding	A	Runs well	17.5 tok/s	11059 ms	151K
Agentic Coding	A	Runs well	17.5 tok/s	16086 ms	151K
Reasoning	A	Runs well	17.5 tok/s	13070 ms	151K
RAG	A	Runs well	17.5 tok/s	20108 ms	151K

Quantization options

How Codestral Mamba 7B (7B params) fits at each quantization level on MacBook Air M2 16GB (11.5 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	A74
Q3_K_S	3	3.4 GB	Low	A75
NVFP4	4	3.9 GB	Medium	A76
Q4_K_M	4	4.3 GB	Medium	A77
Q5_K_M	5	5.0 GB	High	A78
Q6_K	6	5.7 GB	High	A78
Q8_0Best for your GPU	8	7.5 GB	Very High	A77
F16	16	14.3 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral Mamba 7B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "mistralai/Mamba-Codestral-7B-v0.1" \
 --hf-file "Mamba-Codestral-7B-v0.1-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your MacBook Air M2 16GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen 3.5 9B	9B	S	12.7 tok/s
👁 Alibaba Qwen 3 14B	14B	A	6.4 tok/s
👁 Alibaba Qwen 3 8B	8B	S	14.3 tok/s
👁 NVIDIA Nemotron Nano 8B	8B	A	14.3 tok/s
👁 Mistral Ministral 3 14B	14B	B	6.4 tok/s

Frequently asked questions

See all results for MacBook Air M2 16GB See all hardware for Codestral Mamba 7B

URL: https://willitrunai.com/can-run/codestral-mamba-7b-on-m2-air-16gb

⇱ Codestral Mamba 7B on MacBook Air M2 16GB? YES