Can Codestral RAG 19B Pruned i1 run on Mac Studio M2 Ultra 128GB?

YES — Runs Great

C45Usable

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~28.5 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~40 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 28.5 GB, 40.0 tok/s, Runs well

28.5 GB required92.2 GB available

31% VRAM used

Fit status

Runs well

Decode

40.0 tok/s

TTFT

4836 ms

Safe context

473K

Memory

28.5 GB / 92.2 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on Mac Studio M2 Ultra 128GB
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: 40.0 tok/s decode · 4.8s TTFT (warm) · 100 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	C	Runs well	40.0 tok/s	2638 ms	473K
Coding	C	Runs well	40.0 tok/s	4836 ms	473K
Agentic Coding	C	Runs well	40.0 tok/s	7034 ms	473K
Reasoning	C	Runs well	40.0 tok/s	5715 ms	473K
RAG	C	Runs well	40.0 tok/s	8792 ms	473K

Inference speed

Codestral RAG 19B Pruned i1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral RAG 19B Pruned i1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~104 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	103.6	Fits
RTX 4090 24GB	24 GB	Q4_K_M	66.1	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	59.6	Fits
RTX 3090 24GB	24 GB	Q4_K_M	56.5	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	48.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	40.0	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	38.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	36.5	Offloads
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	36.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	36.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.7	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	20.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	19.0	Fits
RTX 4070 12GB	12 GB	Q4_K_M	13.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	8.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	3.1	Too big

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 RAG 19B Pruned i1 (19B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	D39
Q3_K_S	3	9.3 GB	Low	D39
NVFP4	4	10.6 GB	Medium	D39
Q4_K_M	4	11.6 GB	Medium	D39
Q5_K_M	5	13.7 GB	High	D39
Q6_K	6	15.6 GB	High	D40
Q8_0	8	20.3 GB	Very High	C40
F16Best for your GPU	16	38.9 GB	Maximum	C44

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

升级选项

能流畅运行 Codestral RAG 19B Pruned i1 的硬件

RTX PRO 6000 Blackwell Workstation Edition 96GB经济之选

1792 GB/s (+992)

Raises estimated decode speed by about 225%.129.9 tok/s 解码

Raises estimated decode speed by about 225%.

~$9,999 MSRP

RTX PRO 6000 Blackwell Server Edition 96GB最佳性价比

1597 GB/s (+797)

Raises estimated decode speed by about 189%.115.7 tok/s 解码

Raises estimated decode speed by about 189%.

~$9,999 MSRP

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Codestral RAG 19B Pruned i1?

Yes, Mac Studio M2 Ultra 128GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 40.0 tok/s.

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

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 28.5 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 Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Codestral RAG 19B Pruned i1 achieves approximately 40.0 tokens per second decode speed with a time-to-first-token of 4836ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on Mac Studio M2 Ultra 128GB receives a C grade with 40.0 tok/s and 473K context.

What context window can Codestral RAG 19B Pruned i1 use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Codestral RAG 19B Pruned i1 can safely use up to 473K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Codestral RAG 19B Pruned i1?

Not always. Mac Studio M2 Ultra 128GB 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 Studio M2 Ultra 128GB 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-ultra-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: