Can Codestral 22B run on NVIDIA A16 64GB?

YES — Runs Great

B57Good

Estimated from fit model

Codestral 22B needs ~23.5 GB VRAM. NVIDIA A16 64GB has 64.0 GB. With Q4_K_M quantization, expect ~38 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: 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) — 23.5 GB, 37.5 tok/s, Runs well

23.5 GB required64.0 GB available

37% VRAM used

Fit status

Runs well

Decode

37.5 tok/s

TTFT

5164 ms

Safe context

33K

Memory

23.5 GB / 64.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom6.4 GB

See how fast it feels

See how fast it feelsCodestral 22B on NVIDIA A16 64GB
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: 37.5 tok/s decode · 5.2s TTFT (warm) · 94 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	37.5 tok/s	2817 ms	33K
Coding	B	Runs well	37.5 tok/s	5164 ms	33K
Agentic Coding	B	Runs well	37.5 tok/s	7512 ms	33K
Reasoning	B	Runs well	37.5 tok/s	6103 ms	33K
RAG	B	Runs well	37.5 tok/s	9389 ms	33K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	C51
Q3_K_S	3	10.8 GB	Low	C51
NVFP4	4	12.3 GB	Medium	C52
Q4_K_M	4	13.4 GB	Medium	C52
Q5_K_M	5	15.8 GB	High	C52
Q6_K	6	18.0 GB	High	C53
Q8_0	8	23.5 GB	Very High	C54
F16Best for your GPU	16	45.1 GB	Maximum	B58

Get started

Copy-paste commands to run Codestral 22B on your machine.

Run

ollama run codestral

Upgrade options

Hardware that runs Codestral 22B well

RTX PRO 6000 Blackwell Workstation Edition 96GBBudget pick

96 GB VRAM (+32)1792 GB/s (+1192)

Raises estimated decode speed by about 222%.120.6 tok/s decode

Raises estimated decode speed by about 222%.

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

~$9,999 MSRP

RTX PRO 6000 Blackwell Server Edition 96GBBest value

96 GB VRAM (+32)1597 GB/s (+997)

Raises estimated decode speed by about 187%.107.5 tok/s decode

Raises estimated decode speed by about 187%.

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

~$9,999 MSRP

NVIDIA H20 96GBNVIDIA upgrade

96 GB VRAM (+32)4000 GB/s (+3400)

Raises estimated decode speed by about 592%.259.5 tok/s decode

Raises estimated decode speed by about 592%.

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

~$12,000 MSRP

Frequently asked questions

Can NVIDIA A16 64GB run Codestral 22B?

Yes, NVIDIA A16 64GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 37.5 tok/s.

How much VRAM does Codestral 22B need?

Codestral 22B (22B parameters) requires approximately 23.5 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 NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 22B achieves approximately 37.5 tokens per second decode speed with a time-to-first-token of 5164ms using Q4_K_M quantization.

Can NVIDIA A16 64GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on NVIDIA A16 64GB receives a B grade with 37.5 tok/s and 33K context.

What context window can Codestral 22B use on NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for NVIDIA A16 64GB See 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-a16-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

37.5 tok/s

2817 ms

33K

Coding

Runs well

37.5 tok/s

5164 ms

33K

Agentic Coding

Runs well

37.5 tok/s

7512 ms

33K

Reasoning

Runs well

37.5 tok/s

6103 ms

33K

RAG

Runs well

37.5 tok/s

9389 ms

33K

Quantization options

How Codestral 22B (22B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	C51
Q3_K_S	3	10.8 GB	Low	C51
NVFP4	4	12.3 GB	Medium	C52
Q4_K_M	4	13.4 GB	Medium	C52
Q5_K_M	5	15.8 GB	High	C52
Q6_K	6	18.0 GB	High	C53
Q8_0	8	23.5 GB	Very High	C54
F16Best for your GPU	16	45.1 GB	Maximum	B58

Frequently asked questions

Can NVIDIA A16 64GB run Codestral 22B?

Yes, NVIDIA A16 64GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 37.5 tok/s.

How much VRAM does Codestral 22B need?

Codestral 22B (22B parameters) requires approximately 23.5 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 NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 22B achieves approximately 37.5 tokens per second decode speed with a time-to-first-token of 5164ms using Q4_K_M quantization.

Can NVIDIA A16 64GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on NVIDIA A16 64GB receives a B grade with 37.5 tok/s and 33K context.

What context window can Codestral 22B use on NVIDIA A16 64GB?

On NVIDIA A16 64GB, Codestral 22B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.