Is unified memory on Mac mini M4 32GB as fast as VRAM for Codestral RAG 19B Pruned i1?

Not always. Mac mini M4 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.

Can Codestral RAG 19B Pruned i1 run on Mac mini M4 32GB?

Q: What should I upgrade first if Codestral RAG 19B Pruned i1 feels slow on Mac mini M4 32GB?

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.

YES — Runs Great

C48Usable

Estimated — low-sample bucket· few comparable runs

Codestral RAG 19B Pruned i1 needs ~18.2 GB VRAM. Mac mini M4 32GB has 23.0 GB. With Q4_K_M quantization, expect ~8 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) — 18.2 GB, 9.3 tok/s, Runs well

18.2 GB required23.0 GB available

79% VRAM used

Fit status

Runs well

Decode

9.3 tok/s

TTFT

20776 ms

Safe context

51K

Memory

18.2 GB / 23.0 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom3.5 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on Mac mini M4 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: 9.3 tok/s decode · 20.8s TTFT (warm) · 23 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.

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.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	9.3 tok/s	11332 ms	51K
Coding	C	Runs well	7.5 tok/s	25970 ms	51K
Agentic Coding	C	Tight fit	9.3 tok/s	30220 ms	51K
Reasoning	C	Runs well	9.3 tok/s	24554 ms	51K
RAG	C	Tight fit	9.3 tok/s	37775 ms	51K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on Mac mini M4 32GB (23.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C47
Q3_K_S	3	9.3 GB	Low	C48
NVFP4	4

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 options

Hardware that runs Codestral RAG 19B Pruned i1 well

MacBook Pro M3 Pro 36GBBudget pick

36 GB Unified (+4)150 GB/s (+30)

This setup is broadly balanced for this model.9.4 tok/s decode

~$1,999 MSRP

MacBook Pro M4 Max 36GBBest value

36 GB Unified (+4)410 GB/s (+290)

Raises estimated decode speed by about 209%.28.7 tok/s decode

Raises estimated decode speed by about 209%.

~$2,499 MSRP

MacBook Pro M4 Max 48GBApple upgrade

48 GB Unified (+16)546 GB/s (+426)

Raises estimated decode speed by about 287%.36 tok/s decode

Raises estimated decode speed by about 287%.

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

~$2,499 MSRP

Frequently asked questions

Can Mac mini M4 32GB run Codestral RAG 19B Pruned i1?

Yes, Mac mini M4 32GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 7.5 tok/s.

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

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 18.2 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 M4 32GB?

On Mac mini M4 32GB, Codestral RAG 19B Pruned i1 achieves approximately 7.5 tokens per second decode speed with a time-to-first-token of 25970ms using Q4_K_M quantization.

Can Mac mini M4 32GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on Mac mini M4 32GB receives a C grade with 7.5 tok/s and 51K context.

What context window can Codestral RAG 19B Pruned i1 use on Mac mini M4 32GB?

On Mac mini M4 32GB, Codestral RAG 19B Pruned i1 can safely use up to 51K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for Mac mini M4 32GB 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-m4-mini-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: