Can Codestral RAG 19B Pruned i1 run on Mac mini M2 24GB?

YES — With Offload

C45Usable

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~17.3 GB VRAM. Mac mini M2 24GB has 17.3 GB. With Q4_K_M quantization, expect ~6 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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) — 17.3 GB, 5.6 tok/s, Runs with offload (needs ~0 GB host RAM)

17.3 GB required17.3 GB available

100% VRAM used

Fit status

Runs with offload (needs ~0 GB host RAM)

Decode

5.6 tok/s

TTFT

34727 ms

Safe context

16K

Memory

17.3 GB / 17.3 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on Mac mini M2 24GB
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: 5.6 tok/s decode · 34.7s TTFT (warm) · 14 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.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

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.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Tight fit	5.6 tok/s	18829 ms	16K
Coding	C	Runs with offload (needs ~0 GB host RAM)	5.6 tok/s	34727 ms	16K
Agentic Coding	D	Very compromised (needs ~1.3 GB host RAM)	4.6 tok/s	61068 ms	16K
Reasoning	C	Runs with offload (needs ~0 GB host RAM)	5.6 tok/s	41041 ms	16K
RAG	D	Very compromised (needs ~1.3 GB host RAM)	4.6 tok/s	76335 ms	16K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on Mac mini M2 24GB (17.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C50
Q3_K_S	3	9.3 GB	Low	C51
NVFP4	4	10.6 GB	Medium	C50
Q4_K_MBest for your GPU	4	11.6 GB	Medium	C50
Q5_K_M	5	13.7 GB	High	F0
Q6_K	6	15.6 GB	High	F0
Q8_0	8	20.3 GB	Very High	F0
F16	16	38.9 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server start

Upgrade-Optionen

Hardware, die Codestral RAG 19B Pruned i1 gut ausführt

MacBook Pro M4 32GBGünstige Wahl

32 GB Unified (+8)120 GB/s (+20)

Raises estimated decode speed by about 66%.9.3 tok/s Dekodierung

Raises estimated decode speed by about 66%.

Adds memory headroom for longer context windows and future model growth.

ca. $799 MSRP

Mac mini M4 32GBBestes Preis-Leistungs-Verhältnis

32 GB Unified (+8)120 GB/s (+20)

Raises estimated decode speed by about 66%.9.3 tok/s Dekodierung

Raises estimated decode speed by about 66%.

Adds memory headroom for longer context windows and future model growth.

ca. $1,099 MSRP

Mac Studio M2 Ultra 64GBApple-Upgrade

64 GB Unified (+40)800 GB/s (+700)

Raises estimated decode speed by about 614%.40 tok/s Dekodierung

Raises estimated decode speed by about 614%.

Adds memory headroom for longer context windows and future model growth.

ca. $3,999 MSRP

RTX 5090 Laptop 24GBGrößter Sprung

896 GB/s (+796)

Raises estimated decode speed by about 1059%.64.9 tok/s Dekodierung

Raises estimated decode speed by about 1059%.

Adds memory headroom for longer context windows and future model growth.

Frequently asked questions

Can Mac mini M2 24GB run Codestral RAG 19B Pruned i1?

Yes, Mac mini M2 24GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs with offload (needs ~0 GB host RAM)). Expected decode speed: 5.6 tok/s.

How much VRAM does Codestral RAG 19B Pruned i1 need?

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 17.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral RAG 19B Pruned i1?

The recommended quantization for Codestral RAG 19B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral RAG 19B Pruned i1 run at on Mac mini M2 24GB?

On Mac mini M2 24GB, Codestral RAG 19B Pruned i1 achieves approximately 5.6 tokens per second decode speed with a time-to-first-token of 34727ms using Q4_K_M quantization.

Can Mac mini M2 24GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on Mac mini M2 24GB receives a C grade with 5.6 tok/s and 16K context.

What context window can Codestral RAG 19B Pruned i1 use on Mac mini M2 24GB?

On Mac mini M2 24GB, Codestral RAG 19B Pruned i1 can safely use up to 16K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Codestral RAG 19B Pruned i1 feels slow on Mac mini M2 24GB?

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.

Is unified memory on Mac mini M2 24GB as fast as VRAM for Codestral RAG 19B Pruned i1?

Not always. Mac mini M2 24GB 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 Mac mini M2 24GB See all hardware for Codestral RAG 19B Pruned i1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-rag-19b-pruned-i1-gguf-on-m2-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: