VOOZH about

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-rtx-3080-10gb

⇱

Can Codestral 2 25.08 run on RTX 3080 10GB?

NO — Won't Fit

F0Won't run
○Estimated from fit model

Codestral 2 25.08 needs ~17.8 GB but RTX 3080 10GB only has 10.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: MediumStack: StandardBottleneck: Memory capacity
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) — 17.8 GB, exceeds 10.0 GB available
17.8 GB required10.0 GB available
178% VRAM needed

7.8 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

7.5 tok/s

TTFT

25662 ms

Safe context

4K

Memory

17.8 GB / 10.0 GB

Offload

40%

Memory breakdown

Weights13.4 GB
KV Cache2.4 GB
Runtime0.9 GB
Headroom1.0 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsCodestral 2 25.08 on RTX 3080 10GB
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: 7.5 tok/s decode · 25.7s TTFT (warm) · 19 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 17.8 GB, but this setup only exposes 10.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy8.8 tok/s12049 ms4K
CodingFToo heavy7.5 tok/s25662 ms4K
Agentic CodingFToo heavy5.8 tok/s48952 ms4K
ReasoningFToo heavy7.5 tok/s30328 ms4K
RAGFToo heavy5.8 tok/s61189 ms4K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on RTX 3080 10GB (10.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowF0
Q3_K_S
3
10.8 GB
LowF0
NVFP4
4

Upgrade options

Hardware that runs Codestral 2 25.08 well

👁 NVIDIA
RTX 5060 Ti 16GBBest value
16 GB VRAM (+6)
A
Makes the model fit on the accelerator instead of staying completely out of reach.9.1 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.

~$449 MSRP

👁 NVIDIA
RTX 4060 Ti 16GBNVIDIA upgrade
16 GB VRAM (+6)
B
Makes the model fit on the accelerator instead of staying completely out of reach.6.4 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.

~$499 MSRP

👁 NVIDIA
RTX 4000 Ada 20GBBudget pick
20 GB VRAM (+10)
A
Makes the model fit on the accelerator instead of staying completely out of reach.20.1 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.

~$1,250 MSRP

👁 NVIDIA
RTX 5090 Laptop 24GBBiggest leap
24 GB VRAM (+14)896 GB/s (+136)
S
Makes the model fit on the accelerator instead of staying completely out of reach.53.8 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.

Frequently asked questions

See all results for RTX 3080 10GBSee all hardware for Codestral 2 25.08
12.3 GB
Medium
F0
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

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.