Will It Run AI

Can Codestral 2 25.08 run on RX 9060 XT 16GB?

BARELY — Tight on Memory

A71Great
Estimated from fit model

Codestral 2 25.08 needs ~18.4 GB VRAM. RX 9060 XT 16GB has 16.0 GB. With Q4_K_M quantization, expect ~9 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 18.4 GB, 8.5 tok/s, Very compromised (needs ~1.7 GB host RAM)
18.4 GB required16.0 GB available
115% VRAM needed

2.4 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~1.7 GB host RAM)

Decode

8.5 tok/s

TTFT

22721 ms

Safe context

4K

Memory

18.4 GB / 16.0 GB

Offload

10%

Memory breakdown

Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom1.6 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on RX 9060 XT 16GB
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: 8.5 tok/s decode · 22.7s 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.

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.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 1.7 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatARuns with offload (needs ~0.9 GB host RAM)9.8 tok/s10722 ms4K
CodingAVery compromised (needs ~1.7 GB host RAM)8.5 tok/s22721 ms4K
Agentic CodingFToo heavy6.6 tok/s42980 ms4K
ReasoningAVery compromised (needs ~1.7 GB host RAM)8.5 tok/s26852 ms4K
RAGFToo heavy6.6 tok/s53726 ms4K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on RX 9060 XT 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowS86
Q3_K_SBest for your GPU
3
10.8 GB
LowS85
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 2 25.08 on your machine.

Run

lms load codestral-2508 && lms server start

Frequently asked questions

Can RX 9060 XT 16GB run Codestral 2 25.08?

Yes, RX 9060 XT 16GB can run Codestral 2 25.08 with a A grade (Very compromised (needs ~1.7 GB host RAM)). Expected decode speed: 8.5 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 18.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 2 25.08?

The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 2 25.08 run at on RX 9060 XT 16GB?

On RX 9060 XT 16GB, Codestral 2 25.08 achieves approximately 8.5 tokens per second decode speed with a time-to-first-token of 22721ms using Q4_K_M quantization.

Can RX 9060 XT 16GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on RX 9060 XT 16GB receives a A grade with 8.5 tok/s and 4K context.

What context window can Codestral 2 25.08 use on RX 9060 XT 16GB?

On RX 9060 XT 16GB, Codestral 2 25.08 can safely use up to 4K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Codestral 2 25.08 feels slow on RX 9060 XT 16GB?

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.

See all results for RX 9060 XT 16GBSee all hardware for Codestral 2 25.08
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-2-25.08-on-rx-9060-xt-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: