Can Codestral RAG 19B Pruned i1 run on NVIDIA L40 48GB?

YES — Runs Great

C49Usable

Estimated from fit model

Codestral RAG 19B Pruned i1 needs ~19.8 GB VRAM. NVIDIA L40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~58 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) — 19.8 GB, 58.1 tok/s, Runs well

19.8 GB required48.0 GB available

41% VRAM used

Fit status

Runs well

Decode

58.1 tok/s

TTFT

3330 ms

Safe context

219K

Memory

19.8 GB / 48.0 GB

Memory breakdown

Weights11.6 GB

KV Cache2.2 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsCodestral RAG 19B Pruned i1 on NVIDIA L40 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: 58.1 tok/s decode · 3.3s TTFT (warm) · 145 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	C	Runs well	58.1 tok/s	1816 ms	219K
Coding	C	Runs well	58.1 tok/s	3330 ms	219K
Agentic Coding	C	Runs well	58.1 tok/s	4843 ms	219K
Reasoning	C	Runs well	58.1 tok/s	3935 ms	219K
RAG	C	Runs well	58.1 tok/s	6054 ms	219K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C42
Q3_K_S	3	9.3 GB	Low	C42
NVFP4	4	10.6 GB	Medium	C43
Q4_K_M	4	11.6 GB	Medium	C43
Q5_K_M	5	13.7 GB	High	C43
Q6_K	6	15.6 GB	High	C44
Q8_0	8	20.3 GB	Very High	C46
F16Best for your GPU	16	38.9 GB	Maximum	C47

Get started

Copy-paste commands to run Codestral RAG 19B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-rag-19b-pruned-i1-gguf && lms server start

Frequently asked questions

Can NVIDIA L40 48GB run Codestral RAG 19B Pruned i1?

Yes, NVIDIA L40 48GB can run Codestral RAG 19B Pruned i1 with a C grade (Runs well). Expected decode speed: 58.1 tok/s.

How much VRAM does Codestral RAG 19B Pruned i1 need?

Codestral RAG 19B Pruned i1 (19B parameters) requires approximately 19.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral RAG 19B Pruned i1?

The recommended quantization for Codestral RAG 19B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral RAG 19B Pruned i1 run at on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Codestral RAG 19B Pruned i1 achieves approximately 58.1 tokens per second decode speed with a time-to-first-token of 3330ms using Q4_K_M quantization.

Can NVIDIA L40 48GB run Codestral RAG 19B Pruned i1 for coding?

For coding workloads, Codestral RAG 19B Pruned i1 on NVIDIA L40 48GB receives a C grade with 58.1 tok/s and 219K context.

What context window can Codestral RAG 19B Pruned i1 use on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Codestral RAG 19B Pruned i1 can safely use up to 219K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for NVIDIA L40 48GB See all hardware for Codestral RAG 19B 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-rag-19b-pruned-i1-gguf-on-l40-48gb" 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

58.1 tok/s

1816 ms

219K

Coding

Runs well

58.1 tok/s

3330 ms

219K

Agentic Coding

Runs well

58.1 tok/s

4843 ms

219K

Reasoning

Runs well

58.1 tok/s

3935 ms

219K

RAG

Runs well

58.1 tok/s

6054 ms

219K

Quantization options

How Codestral RAG 19B Pruned i1 (19B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	7.4 GB	Low	C42
Q3_K_S	3	9.3 GB	Low	C42
NVFP4	4	10.6 GB	Medium	C43
Q4_K_M	4	11.6 GB	Medium	C43
Q5_K_M	5	13.7 GB	High	C43
Q6_K	6	15.6 GB	High	C44
Q8_0	8	20.3 GB	Very High	C46
F16Best for your GPU	16	38.9 GB	Maximum	C47