Can Leanstral 119B A6B run on Mac Studio M2 Ultra 128GB?

YES — With Q3_K_S

A84Great

Estimated from fit model

Leanstral 119B A6B needs ~83.3 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q3_K_S quantization, expect ~16 tok/s.

Runtime: vLLMCapacity: TightBandwidth: HighStack: OptimizedBottleneck: 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.

Leanstral 119B A6B at Q4_K_M needs 97.6 GB — too much for Mac Studio M2 Ultra 128GB (92.2 GB). Runs at Q3_K_S (83.3 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 97.6 GB, exceeds 92.2 GB available

97.6 GB required92.2 GB available

106% VRAM needed

5.4 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

11.9 tok/s

TTFT

16270 ms

Safe context

Memory

97.6 GB / 92.2 GB

Offload

10%

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom13.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsLeanstral 119B A6B 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: 11.9 tok/s decode · 16.3s TTFT (warm) · 30 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	F	Too heavy	12.7 tok/s	8324 ms	6K
Coding	F	Too heavy	11.9 tok/s	16270 ms	6K
Agentic Coding	F	Too heavy	10.6 tok/s	26679 ms	6K
Reasoning	F	Too heavy	11.9 tok/s	19228 ms	6K
RAG	F	Too heavy	10.6 tok/s	33348 ms	6K

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	A84
Q3_K_S	3	58.3 GB	Low	A84
NVFP4	4	66.6 GB	Medium	A84
Q4_K_MBest for your GPU	4	72.6 GB	Medium	A84
Q5_K_M	5	85.7 GB	High	F0
Q6_K	6	97.6 GB	High	F0
Q8_0	8	127.3 GB	Very High	F0
F16	16	244.0 GB	Maximum	F0

Get started

Copy-paste commands to run Leanstral 119B A6B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Leanstral-2603" \
  --hf-file "Leanstral-2603-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Upgrade-Optionen

Hardware, die Leanstral 119B A6B gut ausführt

Mac Studio M3 Ultra 256GBGünstige Wahl

256 GB Unified (+128)819 GB/s (+19)

Makes the model fit on the accelerator instead of staying completely out of reach.17 tok/s Dekodierung

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.

ca. $6,999 MSRP

AMD Instinct MI350X 288GBBestes Preis-Leistungs-Verhältnis

288 GB VRAM (+160)8000 GB/s (+7200)

Makes the model fit on the accelerator instead of staying completely out of reach.177.9 tok/s Dekodierung

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.

ca. $8,000 MSRP

AMD Instinct MI300A 128GBGrößter Sprung

5300 GB/s (+4500)

Makes the model fit on the accelerator instead of staying completely out of reach.113 tok/s Dekodierung

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.

ca. $12,000 MSRP

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Leanstral 119B A6B?

Yes, Mac Studio M2 Ultra 128GB can run Leanstral 119B A6B at Q3_K_S quantization (Tight fit). The recommended Q4_K_M requires 97.6 GB which exceeds available memory, but at Q3_K_S it needs only 83.3 GB. Expected decode speed: 16.4 tok/s.

How much VRAM does Leanstral 119B A6B need?

Leanstral 119B A6B (119B parameters) requires approximately 97.6 GB at Q4_K_M quantization. On Mac Studio M2 Ultra 128GB, it fits at Q3_K_S using 83.3 GB.

What is the best quantization for Leanstral 119B A6B?

The recommended quantization is Q4_K_M, but on Mac Studio M2 Ultra 128GB the best fitting quantization is Q3_K_S, which uses 83.3 GB.

What speed will Leanstral 119B A6B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Leanstral 119B A6B achieves approximately 16.4 tokens per second decode speed with a time-to-first-token of 11831ms using Q3_K_S quantization.

Can Mac Studio M2 Ultra 128GB run Leanstral 119B A6B for coding?

For coding workloads, Leanstral 119B A6B on Mac Studio M2 Ultra 128GB receives a F grade with 11.9 tok/s and 6K context.

What context window can Leanstral 119B A6B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Leanstral 119B A6B can safely use up to 32K tokens of context at Q3_K_S quantization. The model's official context limit is 256K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Leanstral 119B A6B?

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 Leanstral 119B A6B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/leanstral-119b-a6b-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: