Can Granite 4.1 30B run on Intel Arc Pro B60 24GB?

YES — With Offload

B69Good

Estimated from fit model

Granite 4.1 30B needs ~25.5 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~10 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: MediumStack: StandardBottleneck: Host offload

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) — 25.5 GB, 9.8 tok/s, Runs with offload (needs ~1.1 GB host RAM)

25.5 GB required24.0 GB available

106% VRAM needed

1.5 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~1.1 GB host RAM)

Decode

9.8 tok/s

TTFT

19816 ms

Safe context

10K

Memory

25.5 GB / 24.0 GB

Offload

10%

Memory breakdown

Weights18.3 GB

KV Cache3.9 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsGranite 4.1 30B on Intel Arc Pro B60 24GB
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: 9.8 tok/s decode · 19.8s TTFT (warm) · 24 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

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

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs with offload	14.5 tok/s	7300 ms	10K
Coding	B	Runs with offload (needs ~1.1 GB host RAM)	9.8 tok/s	19816 ms	10K
Agentic Coding	F	Too heavy	7.3 tok/s	38548 ms	10K
Reasoning	B	Runs with offload (needs ~1.1 GB host RAM)	9.8 tok/s	23419 ms	10K
RAG	F	Too heavy	7.3 tok/s	48184 ms	10K

Quantization options

How Granite 4.1 30B (30B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	A83
Q3_K_S	3	14.7 GB	Low	A82
NVFP4	4	16.8 GB	Medium	A82
Q4_K_MBest for your GPU	4	18.3 GB	Medium	A82
Q5_K_M	5	21.6 GB	High	F0
Q6_K	6	24.6 GB	High	F0
Q8_0	8	32.1 GB	Very High	F0
F16	16	61.5 GB	Maximum	F0

Get started

Copy-paste commands to run Granite 4.1 30B on your machine.

Run

ollama run granite4.1:30b

Opções de upgrade

Hardware que roda bem Granite 4.1 30B

NVIDIA A100 40GBMaior salto

40 GB VRAM (+16)1555 GB/s (+1099)

Removes host-memory offload, which is usually the single biggest latency and throughput win.76.7 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Raises estimated decode speed by about 683%.

~$10,000 MSRP

Intel Data Center GPU Max 1550 128GBOpção econômica

128 GB VRAM (+104)3200 GB/s (+2744)

Removes host-memory offload, which is usually the single biggest latency and throughput win.118.4 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Raises estimated decode speed by about 1108%.

~$15,000 MSRP

Gaudi 3 128GBMelhor custo-benefício

128 GB VRAM (+104)3700 GB/s (+3244)

Removes host-memory offload, which is usually the single biggest latency and throughput win.152.1 tok/s decodificação

Removes host-memory offload, which is usually the single biggest latency and throughput win.

Raises estimated decode speed by about 1452%.

~$15,000 MSRP

Frequently asked questions

Can Intel Arc Pro B60 24GB run Granite 4.1 30B?

Yes, Intel Arc Pro B60 24GB can run Granite 4.1 30B with a B grade (Runs with offload (needs ~1.1 GB host RAM)). Expected decode speed: 9.8 tok/s.

How much VRAM does Granite 4.1 30B need?

Granite 4.1 30B (30B parameters) requires approximately 25.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Granite 4.1 30B?

The recommended quantization for Granite 4.1 30B is Q4_K_M, which balances quality and memory efficiency.

What speed will Granite 4.1 30B run at on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Granite 4.1 30B achieves approximately 9.8 tokens per second decode speed with a time-to-first-token of 19816ms using Q4_K_M quantization.

Can Intel Arc Pro B60 24GB run Granite 4.1 30B for coding?

For coding workloads, Granite 4.1 30B on Intel Arc Pro B60 24GB receives a B grade with 9.8 tok/s and 10K context.

What context window can Granite 4.1 30B use on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Granite 4.1 30B can safely use up to 10K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Granite 4.1 30B feels slow on Intel Arc Pro B60 24GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Would CUDA be a better path than Intel Arc Pro B60 24GB for Granite 4.1 30B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Intel Arc Pro B60 24GB See all hardware for Granite 4.1 30B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/granite-4.1-30b-on-arc-pro-b60-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: