Can Codestral 21B Pruned i1 run on Intel Arc Pro B60 24GB?

YES — Runs Great

C51Usable

○Estimated from fit model

Codestral 21B Pruned i1 needs ~18.6 GB VRAM. Intel Arc Pro B60 24GB has 24.0 GB. With Q4_K_M quantization, expect ~19 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 18.6 GB, 19.2 tok/s, Runs well

18.6 GB required24.0 GB available

78% VRAM used

Fit status

Runs well

Decode

19.2 tok/s

TTFT

10072 ms

Safe context

51K

Memory

18.6 GB / 24.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 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: 19.2 tok/s decode · 10.1s TTFT (warm) · 48 tok/s prefill

What limits this setup

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

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.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	19.2 tok/s	5494 ms	51K
Coding	C	Runs well	19.2 tok/s	10072 ms	51K
Agentic Coding	C	Tight fit	19.2 tok/s	14650 ms	51K
Reasoning	C	Runs well	19.2 tok/s	11903 ms	51K
RAG	C	Tight fit	19.2 tok/s	18312 ms	51K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Intel Arc Pro B60 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C47
Q3_K_S	3	10.3 GB	Low	C49
NVFP4	4	11.8 GB	Medium	C50
Q4_K_M	4	12.8 GB	Medium	C50
Q5_K_M	5	15.1 GB	High	C49
Q6_KBest for your GPU	6	17.2 GB	High	C49
Q8_0	8	22.5 GB	Very High	F0
F16	16	43.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 21B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server start

Upgrade options

Hardware that runs Codestral 21B Pruned i1 well

👁 NVIDIA
RTX 5090 32GBBudget pick

32 GB VRAM (+8)1792 GB/s (+1336)

Raises estimated decode speed by about 331%.82.8 tok/s decode

Raises estimated decode speed by about 331%.

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

This is not only a hardware jump. It also gives you a cleaner runtime ecosystem for local LLM tooling.

~$1,999 MSRP

👁 NVIDIA
RTX PRO 4500 Blackwell 32GBBest value

32 GB VRAM (+8)896 GB/s (+440)

Raises estimated decode speed by about 206%.58.8 tok/s decode

Raises estimated decode speed by about 206%.