Can Qwen 2.5 32B run on Intel Arc Pro B60 24GB?

BARELY — Tight on Memory

B70Good

Estimated from fit model

Qwen 2.5 32B needs ~26.7 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~8 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) — 26.7 GB, 8.4 tok/s, Very compromised (needs ~2 GB host RAM)

26.7 GB required24.0 GB available

111% VRAM needed

2.7 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~2 GB host RAM)

Decode

8.4 tok/s

TTFT

23144 ms

Safe context

Memory

26.7 GB / 24.0 GB

Offload

10%

Memory breakdown

Weights19.5 GB

KV Cache3.9 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsQwen 2.5 32B 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: 8.4 tok/s decode · 23.1s TTFT (warm) · 21 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 (needs ~0.6 GB host RAM)	9.8 tok/s	10813 ms	5K
Coding	B	Very compromised (needs ~2 GB host RAM)	8.4 tok/s	23144 ms	5K
Agentic Coding	F	Too heavy	6.3 tok/s	44465 ms	5K
Reasoning	B	Very compromised (needs ~2 GB host RAM)	8.4 tok/s	27352 ms	5K
RAG	F	Too heavy	6.3 tok/s	55581 ms	5K

Quantization options

How Qwen 2.5 32B (32B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	A84
Q3_K_S	3	15.7 GB	Low	A83
NVFP4Best for your GPU	4	17.9 GB	Medium	A83
Q4_K_M	4	19.5 GB	Medium	F0
Q5_K_M	5	23.0 GB	High	F0
Q6_K	6	26.2 GB	High	F0
Q8_0	8	34.2 GB	Very High	F0
F16	16	65.6 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 2.5 32B on your machine.

Run

ollama run qwen2.5

Opciones de mejora

Hardware que ejecuta bien Qwen 2.5 32B

NVIDIA A100 40GBMayor salto

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

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.72.3 tok/s decodificación

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

Sube la velocidad estimada de decodificación alrededor de un 761%.

~$10,000 MSRP

Intel Data Center GPU Max 1550 128GBOpción económica

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

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.111.5 tok/s decodificación

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

Sube la velocidad estimada de decodificación alrededor de un 1227%.

~$15,000 MSRP

Gaudi 3 128GBMejor relación calidad-precio

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

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.143.3 tok/s decodificación

Elimina el offload a memoria del sistema, que suele ser la mayor mejora individual en latencia y throughput.

Sube la velocidad estimada de decodificación alrededor de un 1606%.

~$15,000 MSRP

Frequently asked questions

Can Intel Arc Pro B60 24GB run Qwen 2.5 32B?

Yes, Intel Arc Pro B60 24GB can run Qwen 2.5 32B with a B grade (Very compromised (needs ~2 GB host RAM)). Expected decode speed: 8.4 tok/s.

How much VRAM does Qwen 2.5 32B need?

Qwen 2.5 32B (32B parameters) requires approximately 26.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 2.5 32B?

The recommended quantization for Qwen 2.5 32B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 2.5 32B run at on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Qwen 2.5 32B achieves approximately 8.4 tokens per second decode speed with a time-to-first-token of 23144ms using Q4_K_M quantization.

Can Intel Arc Pro B60 24GB run Qwen 2.5 32B for coding?

For coding workloads, Qwen 2.5 32B on Intel Arc Pro B60 24GB receives a B grade with 8.4 tok/s and 5K context.

What context window can Qwen 2.5 32B use on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Qwen 2.5 32B 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 Qwen 2.5 32B 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 Qwen 2.5 32B?

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 Qwen 2.5 32B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-2.5-32b-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: