Can Laguna XS 2.1 run on Intel Arc Pro B60 24GB?

YES — With Offload

A82Great

Estimated from fit model

Laguna XS 2.1 needs ~24.3 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~26 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: MediumStack: 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) — 24.3 GB, 26.3 tok/s, Runs with offload (needs ~0.2 GB host RAM)

24.3 GB required24.0 GB available

101% VRAM needed

0.3 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.2 GB host RAM)

Decode

26.3 tok/s

TTFT

7365 ms

Safe context

Memory

24.3 GB / 24.0 GB

Memory breakdown

Weights20.4 GB

KV Cache0.6 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsLaguna XS 2.1 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: 26.3 tok/s decode · 7.4s TTFT (warm) · 66 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

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

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	35.2 tok/s	2999 ms	9K
Coding	A	Runs with offload (needs ~0.2 GB host RAM)	26.3 tok/s	7365 ms	9K
Agentic Coding	A	Runs with offload (needs ~0.7 GB host RAM)	25.0 tok/s	11269 ms	9K
Reasoning	A	Runs with offload (needs ~0.2 GB host RAM)	26.3 tok/s	8704 ms	9K
RAG	A	Runs with offload (needs ~0.7 GB host RAM)	25.0 tok/s	14087 ms	9K

Inference speed

Laguna XS 2.1 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Laguna XS 2.1 at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~144 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	144.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	85.8	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	79.6	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	72.3	Offloads
RTX 3090 24GB	24 GB	Q4_K_M	68.5	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	66.3	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	62.9	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	49.2	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	49.2	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	37.7	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	34.6	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	33.1	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	31.3	Too big
RTX 4070 12GB	12 GB	Q4_K_M	10.9	Too big
RTX 3060 12GB	12 GB	Q4_K_M	6.4	Too big
RTX 4060 8GB	8 GB	Q4_K_M	4.6	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Laguna XS 2.1 (33.400001525878906B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q1_0_G128	1.125	4.8 GB	Very Low	A78
Q2_0_G128	1.71	8.9 GB	Low	A80
Q2_K	2	13.0 GB	Low	A82
Q3_K_SBest for your GPU	3	16.4 GB	Low	A81
NVFP4	4	18.7 GB	Medium	F0
Q4_K_M	4	20.4 GB	Medium	F0
Q5_K_M	5	24.0 GB	High	F0
Q6_K	6	27.4 GB	High	F0
Q8_0	8	35.7 GB	Very High	F0
F16	16	68.5 GB	Maximum	F0

Get started

Copy-paste commands to run Laguna XS 2.1 on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "poolside/Laguna-XS-2.1" \
  --hf-file "Laguna-XS-2.1-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your Intel Arc Pro B60 24GB can run

Model	Params	Grade	Decode
Qwen 3.6 35B A3B	35B	B	16.6 tok/s
Qwen 3.5 35B A3B	35B	A	21.9 tok/s
Agents-A1 35B A3B	35.1B	A	23.9 tok/s
Qwen AgentWorld 35B A3B	34.7B	A	24.6 tok/s

Frequently asked questions

Can Intel Arc Pro B60 24GB run Laguna XS 2.1?

Yes, Intel Arc Pro B60 24GB can run Laguna XS 2.1 with a A grade (Runs with offload (needs ~0.2 GB host RAM)). Expected decode speed: 26.3 tok/s.

How much VRAM does Laguna XS 2.1 need?

Laguna XS 2.1 (33.400001525878906B parameters) requires approximately 24.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Laguna XS 2.1?

The recommended quantization for Laguna XS 2.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Laguna XS 2.1 run at on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Laguna XS 2.1 achieves approximately 26.3 tokens per second decode speed with a time-to-first-token of 7365ms using Q4_K_M quantization.

Can Intel Arc Pro B60 24GB run Laguna XS 2.1 for coding?

For coding workloads, Laguna XS 2.1 on Intel Arc Pro B60 24GB receives a A grade with 26.3 tok/s and 9K context.

What context window can Laguna XS 2.1 use on Intel Arc Pro B60 24GB?

On Intel Arc Pro B60 24GB, Laguna XS 2.1 can safely use up to 9K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Laguna XS 2.1 feels slow on Intel Arc Pro B60 24GB?

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.

Would CUDA be a better path than Intel Arc Pro B60 24GB for Laguna XS 2.1?

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 Laguna XS 2.1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/laguna-xs-2.1-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: