Can Granite Code 34B run on Intel Arc Pro B60 24GB?

BARELY — Tight on Memory

B63Good

Estimated from fit model

Granite Code 34B needs ~27.7 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~7 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) — 27.7 GB, 7.3 tok/s, Very compromised (needs ~2.8 GB host RAM)

27.7 GB required24.0 GB available

115% VRAM needed

3.7 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~2.8 GB host RAM)

Decode

7.3 tok/s

TTFT

26375 ms

Safe context

Memory

27.7 GB / 24.0 GB

Offload

10%

Memory breakdown

Weights20.7 GB

KV Cache3.7 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsGranite Code 34B 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: 7.3 tok/s decode · 26.4s TTFT (warm) · 18 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	B	Runs with offload (needs ~1.5 GB host RAM)	8.4 tok/s	12513 ms	4K
Coding	B	Very compromised (needs ~2.8 GB host RAM)	7.3 tok/s	26375 ms	4K
Agentic Coding	F	Too heavy	5.7 tok/s	49422 ms	4K
Reasoning	B	Very compromised (needs ~2.8 GB host RAM)	7.3 tok/s	31171 ms	4K
RAG	F	Too heavy	5.7 tok/s	61778 ms	4K

Quantization options

How Granite Code 34B (34B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.3 GB	Low	A77
Q3_K_SBest for your GPU	3	16.7 GB	Low	A76
NVFP4	4	19.0 GB	Medium	F0
Q4_K_M	4	20.7 GB	Medium	F0
Q5_K_M	5	24.5 GB	High	F0
Q6_K	6	27.9 GB	High	F0
Q8_0	8	36.4 GB	Very High	F0
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

Upgrade-Optionen

Hardware, die Granite Code 34B gut ausführt

NVIDIA A100 40GBGrößter Sprung

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.68.2 tok/s Dekodierung

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

Raises estimated decode speed by about 834%.

ca. $10,000 MSRP

Intel Data Center GPU Max 1550 128GBGünstige Wahl

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.105.3 tok/s Dekodierung

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

Raises estimated decode speed by about 1342%.

ca. $15,000 MSRP

Gaudi 3 128GBBestes Preis-Leistungs-Verhältnis

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

Removes host-memory offload, which is usually the single biggest latency and throughput win.135.3 tok/s Dekodierung

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

Raises estimated decode speed by about 1753%.

ca. $15,000 MSRP

Frequently asked questions

Can Intel Arc Pro B60 24GB run Granite Code 34B?

Yes, Intel Arc Pro B60 24GB can run Granite Code 34B with a B grade (Very compromised (needs ~2.8 GB host RAM)). Expected decode speed: 7.3 tok/s.

How much VRAM does Granite Code 34B need?

Granite Code 34B (34B parameters) requires approximately 27.7 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 Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Granite Code 34B achieves approximately 7.3 tokens per second decode speed with a time-to-first-token of 26375ms using Q4_K_M quantization.

Can Intel Arc Pro B60 24GB run Granite Code 34B for coding?

For coding workloads, Granite Code 34B on Intel Arc Pro B60 24GB receives a B grade with 7.3 tok/s and 4K context.

What context window can Granite Code 34B use on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Granite Code 34B can safely use up to 4K tokens of context. The model's official context limit is 8K, but available memory constrains the safe maximum.

What should I upgrade first if Granite Code 34B 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 Code 34B?

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 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-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: