Can Granite Code 34B run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

A76Great

Estimated from fit model

Granite Code 34B needs ~35.7 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~29 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) — 35.7 GB, 29.1 tok/s, Runs well

35.7 GB required69.1 GB available

52% VRAM used

Fit status

Runs well

Decode

29.1 tok/s

TTFT

6655 ms

Safe context

Memory

35.7 GB / 69.1 GB

Memory breakdown

Weights20.7 GB

KV Cache3.7 GB

Runtime0.9 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsGranite Code 34B on Mac Studio M3 Ultra 96GB
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: 29.1 tok/s decode · 6.7s TTFT (warm) · 73 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	A	Runs well	29.1 tok/s	3630 ms	8K
Coding	A	Runs well	29.1 tok/s	6655 ms	8K
Agentic Coding	A	Runs well	29.1 tok/s	9680 ms	8K
Reasoning	A	Runs well	29.1 tok/s	7865 ms	8K
RAG	A	Runs well	29.1 tok/s	12100 ms	8K

Quantization options

How Granite Code 34B (34B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.3 GB	Low	B69
Q3_K_S	3	16.7 GB	Low	B69
NVFP4	4	19.0 GB	Medium	B70
Q4_K_M	4	20.7 GB	Medium	B70
Q5_K_M	5	24.5 GB	High	A71
Q6_K	6	27.9 GB	High	A72
Q8_0Best for your GPU	8	36.4 GB	Very High	A74
F16	16	69.7 GB	Maximum	F0

Get started

Copy-paste commands to run Granite Code 34B on your machine.

Run

ollama run granite-code:34b

Your hardware

More models your Mac Studio M3 Ultra 96GB can run

Model	Params	Grade	Decode
Qwen 3.6 35B A3B	35B	S	70.8 tok/s
Qwen 3.5 35B A3B	35B	S	77 tok/s
Command A 111B	111B	A	6.8 tok/s
Qwen 2.5 VL 72B	72B	S	13.8 tok/s
Qwen3-Coder-Next	80B	S	37.6 tok/s

Frequently asked questions

Can Mac Studio M3 Ultra 96GB run Granite Code 34B?

Yes, Mac Studio M3 Ultra 96GB can run Granite Code 34B with a A grade (Runs well). Expected decode speed: 29.1 tok/s.

How much VRAM does Granite Code 34B need?

Granite Code 34B (34B parameters) requires approximately 35.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite Code 34B?

The recommended quantization for Granite Code 34B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite Code 34B run at on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Granite Code 34B achieves approximately 29.1 tokens per second decode speed with a time-to-first-token of 6655ms using Q4_K_M quantization.

Can Mac Studio M3 Ultra 96GB run Granite Code 34B for coding?

For coding workloads, Granite Code 34B on Mac Studio M3 Ultra 96GB receives a A grade with 29.1 tok/s and 8K context.

What context window can Granite Code 34B use on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Granite Code 34B can safely use up to 8K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M3 Ultra 96GB as fast as VRAM for Granite Code 34B?

Not always. Mac Studio M3 Ultra 96GB 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 M3 Ultra 96GB See all hardware for Granite Code 34B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/granite-code-34b-on-m3-ultra-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

29.1 tok/s

3630 ms

Coding

Runs well

29.1 tok/s

6655 ms

Agentic Coding

Runs well

29.1 tok/s

9680 ms

Reasoning

Runs well

29.1 tok/s

7865 ms

RAG

Runs well

29.1 tok/s

12100 ms

Quantization options

How Granite Code 34B (34B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.3 GB	Low	B69
Q3_K_S	3	16.7 GB	Low	B69
NVFP4	4	19.0 GB	Medium	B70
Q4_K_M	4	20.7 GB	Medium	B70
Q5_K_M	5	24.5 GB	High	A71
Q6_K	6	27.9 GB	High	A72
Q8_0Best for your GPU	8	36.4 GB	Very High	A74
F16	16	69.7 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen 3.6 35B A3B

35B

70.8 tok/s

Qwen 3.5 35B A3B

35B

77 tok/s

Command A 111B

111B

6.8 tok/s

Qwen 2.5 VL 72B

72B

13.8 tok/s

Qwen3-Coder-Next

80B

37.6 tok/s