VOOZH about

URL: https://willitrunai.com/can-run/codestral-22b-on-arc-pro-a60-12gb

⇱ Codestral 22B on Intel Arc Pro A60 12GB? No — Alternatives

Can Codestral 22B run on Intel Arc Pro A60 12GB?

YES — With Q2_K

C48Usable
○Estimated from fit model

Codestral 22B needs ~13.1 GB VRAM. Intel Arc Pro A60 12GB has 12.0 GB. With Q2_K quantization, expect ~13 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: Host offload
Share:

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.

Codestral 22B at Q4_K_M needs 18.0 GB — too much for Intel Arc Pro A60 12GB (12.0 GB). Runs at Q2_K (13.1 GB) with low quality.
Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 18.0 GB, exceeds 12.0 GB available
18.0 GB required12.0 GB available
150% VRAM needed

6.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

4.8 tok/s

TTFT

40029 ms

Safe context

4K

Memory

18.0 GB / 12.0 GB

Offload

30%

Memory breakdown

Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom1.2 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsCodestral 22B on Intel Arc Pro A60 12GB
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: 4.8 tok/s decode · 40.0s TTFT (warm) · 12 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

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy5.6 tok/s18827 ms4K
CodingFToo heavy4.8 tok/s40029 ms4K
Agentic CodingFToo heavy3.7 tok/s76139 ms4K
ReasoningFToo heavy4.8 tok/s47307 ms4K
RAGFToo heavy3.7 tok/s95174 ms4K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on Intel Arc Pro A60 12GB (12.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowF0
Q3_K_S
3
10.8 GB
LowF0
NVFP4
4
12.3 GB
MediumF0
Q4_K_M
4
13.4 GB
MediumF0
Q5_K_M
5
15.8 GB
HighF0
Q6_K
6
18.0 GB
HighF0
Q8_0
8
23.5 GB
Very HighF0
F16
16
45.1 GB
MaximumF0

Get started

Copy-paste commands to run Codestral 22B on your machine.

Run

ollama run codestral

Upgrade options

Hardware that runs Codestral 22B well

👁 Intel
Intel Arc A770 16GBBest value
16 GB VRAM (+4)560 GB/s (+176)
C
Makes the model fit on the accelerator instead of staying completely out of reach.11.3 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 135%.

~$349 MSRP

👁 Intel
Intel Arc Pro B50 16GBIntel upgrade
16 GB VRAM (+4)
C
Makes the model fit on the accelerator instead of staying completely out of reach.5.6 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Adds memory headroom for longer context windows and future model growth.

~$399 MSRP

👁 Intel
Intel Arc Pro B60 24GBBudget pick
24 GB VRAM (+12)456 GB/s (+72)
B
Makes the model fit on the accelerator instead of staying completely out of reach.19.7 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

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

~$599 MSRP

Frequently asked questions

See all results for Intel Arc Pro A60 12GBSee all hardware for Codestral 22B