Can Codestral 22B run on NVIDIA B200 180GB?

YES — Runs Great

B56Good

Estimated from fit model

Codestral 22B needs ~35.1 GB VRAM. NVIDIA B200 180GB has 180.0 GB. With Q4_K_M quantization, expect ~308 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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) — 35.1 GB, 308.0 tok/s, Runs well

35.1 GB required180.0 GB available

20% VRAM used

Fit status

Runs well

Decode

308.0 tok/s

TTFT

629 ms

Safe context

33K

Memory

35.1 GB / 180.0 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom18.0 GB

See how fast it feels

See how fast it feelsCodestral 22B on NVIDIA B200 180GB
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: 308.0 tok/s decode · 629ms TTFT (warm) · 770 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	308.0 tok/s	350 ms	33K
Coding	B	Runs well	308.0 tok/s	629 ms	33K
Agentic Coding	B	Runs well	308.0 tok/s	914 ms	33K
Reasoning	B	Runs well	308.0 tok/s	743 ms	33K
RAG	B	Runs well	308.0 tok/s	1143 ms	33K

Inference speed

Codestral 22B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Codestral 22B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~96 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	96.2	Fits
RTX 4090 24GB	24 GB	Q4_K_M	61.4	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	55.4	Fits
RTX 3090 24GB	24 GB	Q4_K_M	52.5	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	44.6	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	37.4	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	37.4	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	37.2	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	35.2	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	26.5	Heavy offload
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	23.6	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	19.2	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	17.6	Fits
RTX 4070 12GB	12 GB	Q4_K_M	9.4	Too big
RTX 3060 12GB	12 GB	Q4_K_M	5.9	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.4	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Codestral 22B (22B params) fits at each quantization level on NVIDIA B200 180GB (180.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	C47
Q3_K_S	3	10.8 GB	Low	C47
NVFP4	4	12.3 GB	Medium	C47
Q4_K_M	4	13.4 GB	Medium	C47
Q5_K_M	5	15.8 GB	High	C47
Q6_K	6	18.0 GB	High	C48
Q8_0	8	23.5 GB	Very High	C48
F16Best for your GPU	16	45.1 GB	Maximum	C51

Get started

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

Run

ollama run codestral

Frequently asked questions

Can NVIDIA B200 180GB run Codestral 22B?

Yes, NVIDIA B200 180GB can run Codestral 22B with a B grade (Runs well). Expected decode speed: 308.0 tok/s.

How much VRAM does Codestral 22B need?

Codestral 22B (22B parameters) requires approximately 35.1 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 B200 180GB?

On NVIDIA B200 180GB, Codestral 22B achieves approximately 308.0 tokens per second decode speed with a time-to-first-token of 629ms using Q4_K_M quantization.

Can NVIDIA B200 180GB run Codestral 22B for coding?

For coding workloads, Codestral 22B on NVIDIA B200 180GB receives a B grade with 308.0 tok/s and 33K context.

What context window can Codestral 22B use on NVIDIA B200 180GB?

On NVIDIA B200 180GB, 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 B200 180GB 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-b200-180gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: