Can Codestral Mamba 7B run on MacBook Pro M1 Max 32GB?

YES — Runs Great

A74Great

Estimated from fit model

Codestral Mamba 7B needs ~9.1 GB VRAM. MacBook Pro M1 Max 32GB has 23.0 GB. With Q4_K_M quantization, expect ~59 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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

Q4_K_M (Medium quality) — 9.1 GB, 59.3 tok/s, Runs well

9.1 GB required23.0 GB available

40% VRAM used

Fit status

Runs well

Decode

59.3 tok/s

TTFT

3267 ms

Safe context

262K

Memory

9.1 GB / 23.0 GB

Memory breakdown

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom3.5 GB

See how fast it feels

See how fast it feelsCodestral Mamba 7B on MacBook Pro M1 Max 32GB
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: 59.3 tok/s decode · 3.3s TTFT (warm) · 148 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	59.3 tok/s	1782 ms	262K
Coding	A	Runs well	59.3 tok/s	3267 ms	262K
Agentic Coding	A	Runs well	59.3 tok/s	4753 ms	262K
Reasoning	A	Runs well	59.3 tok/s	3862 ms	262K
RAG	A	Runs well	59.3 tok/s	5941 ms	262K

Inference speed

Codestral Mamba 7B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral Mamba 7B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~98 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	98.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	98.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	98.0	Fits
RTX 3090 24GB	24 GB	Q4_K_M	98.0	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	98.0	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	98.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	98.0	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	92.6	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	92.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	88.5	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	64.6	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	59.3	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	56.6	Fits
RTX 3060 12GB	12 GB	Q4_K_M	55.6	Fits
RTX 4060 8GB	8 GB	Q4_K_M	53.5	Fits

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Codestral Mamba 7B (7B params) fits at each quantization level on MacBook Pro M1 Max 32GB (23.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	B70
Q3_K_S	3	3.4 GB	Low	B70
NVFP4	4	3.9 GB	Medium	A70
Q4_K_M	4	4.3 GB	Medium	A70
Q5_K_M	5	5.0 GB	High	A71
Q6_K	6	5.7 GB	High	A71
Q8_0	8	7.5 GB	Very High	A72
F16Best for your GPU	16	14.3 GB	Maximum	A75

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 Pro M1 Max 32GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	A	29.9 tok/s
Qwen 3.5 27B	27B	S	13.3 tok/s
Qwen 3.6 27B	27B	S	11 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	31.5 tok/s
Qwen 3.5 9B	9B	S	43.1 tok/s

Frequently asked questions

Can MacBook Pro M1 Max 32GB run Codestral Mamba 7B?

Yes, MacBook Pro M1 Max 32GB can run Codestral Mamba 7B with a A grade (Runs well). Expected decode speed: 59.3 tok/s.

How much VRAM does Codestral Mamba 7B need?

Codestral Mamba 7B (7B parameters) requires approximately 9.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral Mamba 7B?

The recommended quantization for Codestral Mamba 7B is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral Mamba 7B run at on MacBook Pro M1 Max 32GB?

On MacBook Pro M1 Max 32GB, Codestral Mamba 7B achieves approximately 59.3 tokens per second decode speed with a time-to-first-token of 3267ms using Q4_K_M quantization.

Can MacBook Pro M1 Max 32GB run Codestral Mamba 7B for coding?

For coding workloads, Codestral Mamba 7B on MacBook Pro M1 Max 32GB receives a A grade with 59.3 tok/s and 262K context.

What context window can Codestral Mamba 7B use on MacBook Pro M1 Max 32GB?

On MacBook Pro M1 Max 32GB, Codestral Mamba 7B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

Is unified memory on MacBook Pro M1 Max 32GB as fast as VRAM for Codestral Mamba 7B?

Not always. MacBook Pro M1 Max 32GB 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 Pro M1 Max 32GB See all hardware for Codestral Mamba 7B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-mamba-7b-on-m1-max-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: