Can Codestral RAG 19B Pruned i1 run on MacBook Pro M3 Pro 18GB?

YES — With Q3_K_S

D36Poor

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~14.4 GB VRAM. MacBook Pro M3 Pro 18GB has 13.0 GB. With Q3_K_S quantization, expect ~9 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: Very lowStack: StandardBottleneck: Host offload

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.

Codestral RAG 19B Pruned i1 at Q4_K_M needs 16.7 GB — too much for MacBook Pro M3 Pro 18GB (13.0 GB). Runs at Q3_K_S (14.4 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 16.7 GB, exceeds 13.0 GB available

16.7 GB required13.0 GB available

128% VRAM needed

3.7 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

6.6 tok/s

TTFT

29278 ms

Safe context

Memory

16.7 GB / 13.0 GB

Offload

20%

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom1.9 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsCodestral RAG 19B Pruned i1 on MacBook Pro M3 Pro 18GB
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: 6.6 tok/s decode · 29.3s TTFT (warm) · 17 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

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

Increase host RAM if you keep offloading

This setup may need roughly 0.9 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	D	Very compromised (needs ~1.9 GB host RAM)	7.2 tok/s	14672 ms	4K
Coding	F	Too heavy	6.6 tok/s	29278 ms	4K
Agentic Coding	F	Too heavy	5.7 tok/s	49321 ms	4K
Reasoning	F	Too heavy	6.6 tok/s	34601 ms	4K
RAG	F	Too heavy	5.7 tok/s	61652 ms	4K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on MacBook Pro M3 Pro 18GB (13.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C51
Q3_K_SBest for your GPU	3	9.3 GB	Low	C51
NVFP4	4	10.6 GB	Medium	F0
Q4_K_M	4	11.6 GB	Medium	F0
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

アップグレードオプション

Codestral RAG 19B Pruned i1を快適に動かすハードウェア

MacBook Pro M4 32GBコスパ重視

32 GB Unified (+14)

Makes the model fit on the accelerator instead of staying completely out of reach.9.3 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

〜$799 MSRP

Mac mini M4 32GBコスパ最良

32 GB Unified (+14)

Makes the model fit on the accelerator instead of staying completely out of reach.9.3 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

〜$1,099 MSRP

MacBook Air M4 24GBAppleアップグレード

24 GB Unified (+6)

Makes the model fit on the accelerator instead of staying completely out of reach.9.3 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

〜$1,099 MSRP

RTX 5090 Laptop 24GB最大の飛躍

24 GB VRAM (+6)896 GB/s (+746)

Makes the model fit on the accelerator instead of staying completely out of reach.64.9 tok/sデコード

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Frequently asked questions

Can MacBook Pro M3 Pro 18GB run Codestral RAG 19B Pruned i1?

Yes, MacBook Pro M3 Pro 18GB can run Codestral RAG 19B Pruned i1 at Q3_K_S quantization (Very compromised (needs ~0.9 GB host RAM)). The recommended Q4_K_M requires 16.7 GB which exceeds available memory, but at Q3_K_S it needs only 14.4 GB. Expected decode speed: 9.2 tok/s.

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

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 16.7 GB at Q4_K_M quantization. On MacBook Pro M3 Pro 18GB, it fits at Q3_K_S using 14.4 GB.

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

The recommended quantization is Q4_K_M, but on MacBook Pro M3 Pro 18GB the best fitting quantization is Q3_K_S, which uses 14.4 GB.

What speed will Codestral RAG 19B Pruned i1 run at on MacBook Pro M3 Pro 18GB?

On MacBook Pro M3 Pro 18GB, Codestral RAG 19B Pruned i1 achieves approximately 9.2 tokens per second decode speed with a time-to-first-token of 20994ms using Q3_K_S quantization.

Can MacBook Pro M3 Pro 18GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on MacBook Pro M3 Pro 18GB receives a F grade with 6.6 tok/s and 4K context.

What context window can Codestral RAG 19B Pruned i1 use on MacBook Pro M3 Pro 18GB?

On MacBook Pro M3 Pro 18GB, Codestral RAG 19B Pruned i1 can safely use up to 6K tokens of context at Q3_K_S quantization. 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 MacBook Pro M3 Pro 18GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Is unified memory on MacBook Pro M3 Pro 18GB as fast as VRAM for Codestral RAG 19B Pruned i1?

Not always. MacBook Pro M3 Pro 18GB 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 M3 Pro 18GB 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-m3-pro-18gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: