Will It Run AI

Can Pixtral Large 124B run on Mac Studio M1 Ultra 128GB?

YES — With Offload

A85Great
Estimated from fit model

Pixtral Large 124B needs ~95.7 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~6 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Memory bandwidth
Share:

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) — 95.7 GB, 5.9 tok/s, Runs with offload (needs ~2.8 GB host RAM)
95.7 GB required92.2 GB available
104% VRAM needed

3.5 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~2.8 GB host RAM)

Decode

5.9 tok/s

TTFT

32981 ms

Safe context

5K

Memory

95.7 GB / 92.2 GB

Memory breakdown

Weights75.6 GB
KV Cache5.4 GB
Runtime0.9 GB
Headroom13.8 GB

See how fast it feels

See how fast it feelsPixtral Large 124B on Mac Studio M1 Ultra 128GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 5.9 tok/s decode · 33.0s TTFT (warm) · 15 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

WorkloadGradeFitDecodeTTFTContext
ChatARuns with offload (needs ~0.7 GB host RAM)6.2 tok/s17107 ms5K
CodingARuns with offload (needs ~2.8 GB host RAM)5.9 tok/s32981 ms5K
Agentic CodingAVery compromised (needs ~6.7 GB host RAM)5.4 tok/s51985 ms5K
ReasoningARuns with offload (needs ~2.8 GB host RAM)5.9 tok/s38977 ms5K
RAGAVery compromised (needs ~6.7 GB host RAM)5.4 tok/s64982 ms5K

Quantization options

How Pixtral Large 124B (124B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
48.4 GB
LowS87
Q3_K_S
3
60.8 GB
LowS87
NVFP4Best for your GPU
4
69.4 GB
MediumS87
Q4_K_M
4
75.6 GB
MediumF0
Q5_K_M
5
89.3 GB
HighF0
Q6_K
6
101.7 GB
HighF0
Q8_0
8
132.7 GB
Very HighF0
F16
16
254.2 GB
MaximumF0

Get started

Copy-paste commands to run Pixtral Large 124B on your machine.

Run

lms load Pixtral-Large-Instruct-2411 && lms server start

Frequently asked questions

Can Mac Studio M1 Ultra 128GB run Pixtral Large 124B?

Yes, Mac Studio M1 Ultra 128GB can run Pixtral Large 124B with a A grade (Runs with offload (needs ~2.8 GB host RAM)). Expected decode speed: 5.9 tok/s.

How much VRAM does Pixtral Large 124B need?

Pixtral Large 124B (124B parameters) requires approximately 95.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Pixtral Large 124B?

The recommended quantization for Pixtral Large 124B is Q4_K_M, which balances quality and memory efficiency.

What speed will Pixtral Large 124B run at on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, Pixtral Large 124B achieves approximately 5.9 tokens per second decode speed with a time-to-first-token of 32981ms using Q4_K_M quantization.

Can Mac Studio M1 Ultra 128GB run Pixtral Large 124B for coding?

For coding workloads, Pixtral Large 124B on Mac Studio M1 Ultra 128GB receives a A grade with 5.9 tok/s and 5K context.

What context window can Pixtral Large 124B use on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, Pixtral Large 124B can safely use up to 5K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Pixtral Large 124B feels slow on Mac Studio M1 Ultra 128GB?

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 Studio M1 Ultra 128GB as fast as VRAM for Pixtral Large 124B?

Not always. Mac Studio M1 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 M1 Ultra 128GBSee all hardware for Pixtral Large 124B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/pixtral-large-124b-on-m1-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: