Will It Run AI

Can Codestral 22B v0.1 run on RX 9060 8GB?

NO — Won't Fit

F0Won't run
Estimated from fit model

Codestral 22B v0.1 needs ~17.7 GB but RX 9060 8GB only has 8.0 GB. Try a smaller quantization or lighter model.

Runtime: llama.cppCapacity: No fitBandwidth: LowStack: 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) — 17.7 GB, exceeds 8.0 GB available
17.7 GB required8.0 GB available
221% VRAM needed

9.7 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.0 tok/s

TTFT

95463 ms

Safe context

4K

Memory

17.7 GB / 8.0 GB

Offload

50%

Memory breakdown

Weights13.4 GB
KV Cache2.6 GB
Runtime0.9 GB
Headroom0.8 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsCodestral 22B v0.1 on RX 9060 8GB
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: 2.0 tok/s decode · 95.5s TTFT (warm) · 5 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 17.7 GB, but this setup only exposes 8.0 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 heavy2.2 tok/s47246 ms4K
CodingFToo heavy2.0 tok/s95463 ms4K
Agentic CodingFToo heavy2.0 tok/s138855 ms4K
ReasoningFToo heavy2.0 tok/s112820 ms4K
RAGFToo heavy2.0 tok/s173568 ms4K

Quantization options

How Codestral 22B v0.1 (22B params) fits at each quantization level on RX 9060 8GB (8.0 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

升级选项

能流畅运行 Codestral 22B v0.1 的硬件

RX 7600 XT 16GB最佳性价比
16 GB VRAM (+8)
D
Makes the model fit on the accelerator instead of staying completely out of reach.6.9 tok/s 解码

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

Raises estimated decode speed by about 245%.

~$329 MSRP

RX 9060 XT 16GBAMD 升级
16 GB VRAM (+8)320 GB/s (+32)
D
Makes the model fit on the accelerator instead of staying completely out of reach.8.3 tok/s 解码

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

Raises estimated decode speed by about 315%.

~$349 MSRP

RX 7900 XT 20GB经济之选
20 GB VRAM (+12)800 GB/s (+512)
C
Makes the model fit on the accelerator instead of staying completely out of reach.35.8 tok/s 解码

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.

~$899 MSRP

Frequently asked questions

Can RX 9060 8GB run Codestral 22B v0.1?

No, Codestral 22B v0.1 requires more memory than RX 9060 8GB provides.

How much VRAM does Codestral 22B v0.1 need?

Codestral 22B v0.1 (22B parameters) requires approximately 17.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 22B v0.1?

The recommended quantization for Codestral 22B v0.1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 22B v0.1 run at on RX 9060 8GB?

On RX 9060 8GB, Codestral 22B v0.1 achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 95463ms using Q4_K_M quantization.

Can RX 9060 8GB run Codestral 22B v0.1 for coding?

For coding workloads, Codestral 22B v0.1 on RX 9060 8GB receives a F grade with 2.0 tok/s and 4K context.

What context window can Codestral 22B v0.1 use on RX 9060 8GB?

On RX 9060 8GB, Codestral 22B v0.1 can safely use up to 4K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if Codestral 22B v0.1 feels slow on RX 9060 8GB?

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.

See all results for RX 9060 8GBSee all hardware for Codestral 22B v0.1
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lmstudio-community--codestral-22b-v0-1-gguf-on-rx-9060-8gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: