Can Codestral 21B Pruned i1 run on Quadro RTX 8000 48GB?

YES — Runs Great

C48Usable

Estimated from fit model

Codestral 21B Pruned i1 needs ~21.3 GB VRAM. Quadro RTX 8000 48GB has 48.0 GB. With Q4_K_M quantization, expect ~36 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) — 21.3 GB, 36.2 tok/s, Runs well

21.3 GB required48.0 GB available

44% VRAM used

Fit status

Runs well

Decode

36.2 tok/s

TTFT

5349 ms

Safe context

190K

Memory

21.3 GB / 48.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on Quadro RTX 8000 48GB
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: 36.2 tok/s decode · 5.3s TTFT (warm) · 91 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	C	Runs well	36.2 tok/s	2917 ms	190K
Coding	C	Runs well	36.2 tok/s	5349 ms	190K
Agentic Coding	C	Runs well	36.2 tok/s	7780 ms	190K
Reasoning	C	Runs well	36.2 tok/s	6321 ms	190K
RAG	C	Runs well	36.2 tok/s	9725 ms	190K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Quadro RTX 8000 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C42
Q3_K_S	3	10.3 GB	Low	C43
NVFP4	4	11.8 GB	Medium	C43
Q4_K_M	4	12.8 GB	Medium	C43
Q5_K_M	5	15.1 GB	High	C44
Q6_K	6	17.2 GB	High	C45
Q8_0Best for your GPU	8	22.5 GB	Very High	C46
F16	16	43.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 21B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server start

Upgrade options

Hardware that runs Codestral 21B Pruned i1 well

NVIDIA A100 80GBBudget pick

80 GB VRAM (+32)2039 GB/s (+1367)

Raises estimated decode speed by about 269%.133.7 tok/s decode

Raises estimated decode speed by about 269%.

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

~$15,000 MSRP

NVIDIA A800 80GBBest value

80 GB VRAM (+32)1935 GB/s (+1263)

Raises estimated decode speed by about 225%.117.8 tok/s decode

Raises estimated decode speed by about 225%.

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

~$15,000 MSRP

NVIDIA H800 80GBNVIDIA upgrade

80 GB VRAM (+32)3000 GB/s (+2328)

Raises estimated decode speed by about 424%.189.7 tok/s decode

Raises estimated decode speed by about 424%.

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

~$30,000 MSRP

Frequently asked questions

Can Quadro RTX 8000 48GB run Codestral 21B Pruned i1?

Yes, Quadro RTX 8000 48GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 36.2 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 21.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on Quadro RTX 8000 48GB?

On Quadro RTX 8000 48GB, Codestral 21B Pruned i1 achieves approximately 36.2 tokens per second decode speed with a time-to-first-token of 5349ms using Q4_K_M quantization.

Can Quadro RTX 8000 48GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on Quadro RTX 8000 48GB receives a C grade with 36.2 tok/s and 190K context.

What context window can Codestral 21B Pruned i1 use on Quadro RTX 8000 48GB?

On Quadro RTX 8000 48GB, Codestral 21B Pruned i1 can safely use up to 190K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for Quadro RTX 8000 48GB See all hardware for Codestral 21B Pruned i1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-21b-pruned-i1-gguf-on-quadro-rtx-8000-48gb" 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

36.2 tok/s

2917 ms

190K

Coding

Runs well

36.2 tok/s

5349 ms

190K

Agentic Coding

Runs well

36.2 tok/s

7780 ms

190K

Reasoning

Runs well

36.2 tok/s

6321 ms

190K

RAG

Runs well

36.2 tok/s

9725 ms

190K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Quadro RTX 8000 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C42
Q3_K_S	3	10.3 GB	Low	C43
NVFP4	4	11.8 GB	Medium	C43
Q4_K_M	4	12.8 GB	Medium	C43
Q5_K_M	5	15.1 GB	High	C44
Q6_K	6	17.2 GB	High	C45
Q8_0Best for your GPU	8	22.5 GB	Very High	C46
F16	16	43.1 GB	Maximum	F0

Frequently asked questions

Can Quadro RTX 8000 48GB run Codestral 21B Pruned i1?

Yes, Quadro RTX 8000 48GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 36.2 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 21.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on Quadro RTX 8000 48GB?

On Quadro RTX 8000 48GB, Codestral 21B Pruned i1 achieves approximately 36.2 tokens per second decode speed with a time-to-first-token of 5349ms using Q4_K_M quantization.

Can Quadro RTX 8000 48GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on Quadro RTX 8000 48GB receives a C grade with 36.2 tok/s and 190K context.

What context window can Codestral 21B Pruned i1 use on Quadro RTX 8000 48GB?

On Quadro RTX 8000 48GB, Codestral 21B Pruned i1 can safely use up to 190K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.