Will It Run AI

Can Codestral 22B run on Radeon PRO W7700 16GB?

BARELY — Tight on Memory

C48Usable
Estimated from fit model

Codestral 22B needs ~18.4 GB VRAM. Radeon PRO W7700 16GB has 16.0 GB. With Q4_K_M quantization, expect ~15 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: MediumStack: 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, 15.3 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

15.3 tok/s

TTFT

12670 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 22B on Radeon PRO W7700 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: 15.3 tok/s decode · 12.7s TTFT (warm) · 38 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
ChatCRuns with offload (needs ~0.9 GB host RAM)17.7 tok/s5979 ms4K
CodingCVery compromised (needs ~1.7 GB host RAM)15.3 tok/s12670 ms4K
Agentic CodingFToo heavy11.7 tok/s23967 ms4K
ReasoningCVery compromised (needs ~1.7 GB host RAM)15.3 tok/s14973 ms4K
RAGFToo heavy11.7 tok/s29959 ms4K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on Radeon PRO W7700 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowB61
Q3_K_SBest for your GPU
3
10.8 GB
LowB61
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

升级选项

能流畅运行 Codestral 22B 的硬件

RX 7900 XT 20GB经济之选
20 GB VRAM (+4)800 GB/s (+224)
B
Removes host-memory offload, which is usually the single biggest latency and throughput win.38.5 tok/s 解码

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

Raises estimated decode speed by about 152%.

~$899 MSRP

RX 7900 XTX 24GB最佳性价比
24 GB VRAM (+8)960 GB/s (+384)
B
Removes host-memory offload, which is usually the single biggest latency and throughput win.55.4 tok/s 解码

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

Raises estimated decode speed by about 262%.

~$999 MSRP

Radeon AI PRO R9700 32GBAMD 升级
32 GB VRAM (+16)640 GB/s (+64)
B
Removes host-memory offload, which is usually the single biggest latency and throughput win.30.2 tok/s 解码

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

Raises estimated decode speed by about 97%.

~$1,899 MSRP

Frequently asked questions

Can Radeon PRO W7700 16GB run Codestral 22B?

Yes, Radeon PRO W7700 16GB can run Codestral 22B with a C grade (Very compromised (needs ~1.7 GB host RAM)). Expected decode speed: 15.3 tok/s.

How much VRAM does Codestral 22B need?

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

What is the best quantization for Codestral 22B?

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

What speed will Codestral 22B run at on Radeon PRO W7700 16GB?

On Radeon PRO W7700 16GB, Codestral 22B achieves approximately 15.3 tokens per second decode speed with a time-to-first-token of 12670ms using Q4_K_M quantization.

Can Radeon PRO W7700 16GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on Radeon PRO W7700 16GB receives a C grade with 15.3 tok/s and 4K context.

What context window can Codestral 22B use on Radeon PRO W7700 16GB?

On Radeon PRO W7700 16GB, Codestral 22B can safely use up to 4K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

What should I upgrade first if Codestral 22B feels slow on Radeon PRO W7700 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 Radeon PRO W7700 16GBSee all hardware for Codestral 22B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-22b-on-radeon-pro-w7700-16gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: