Can CodeLlama 13B Instruct run on NVIDIA L4 24GB?

YES — With Offload

A75Great

Estimated from fit model

CodeLlama 13B Instruct needs ~23.4 GB VRAM. NVIDIA L4 24GB has 24.0 GB. With Q4_K_M quantization, expect ~26 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: StandardBottleneck: 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) — 23.4 GB, 25.8 tok/s, Runs with offload

23.4 GB required24.0 GB available

98% VRAM used

Fit status

Runs with offload

Decode

25.8 tok/s

TTFT

7498 ms

Safe context

16K

Memory

23.4 GB / 24.0 GB

Memory breakdown

Weights7.9 GB

KV Cache12.2 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsCodeLlama 13B Instruct on NVIDIA L4 24GB
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: 25.8 tok/s decode · 7.5s TTFT (warm) · 65 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

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

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	25.8 tok/s	4090 ms	16K
Coding	A	Runs with offload	25.8 tok/s	7498 ms	16K
Agentic Coding	F	Too heavy	8.4 tok/s	33436 ms	16K
Reasoning	A	Runs with offload	25.8 tok/s	8861 ms	16K
RAG	F	Too heavy	8.4 tok/s	41794 ms	16K

Inference speed

CodeLlama 13B Instruct inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for CodeLlama 13B Instruct at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~151 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	151.4	Fits
RTX 4090 24GB	24 GB	Q4_K_M	96.6	Offloads
RX 7900 XTX 24GB	24 GB	Q4_K_M	87.2	Offloads
RTX 3090 24GB	24 GB	Q4_K_M	82.6	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	70.2	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	58.5	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	55.5	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	38.2	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	38.2	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	30.3	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	27.7	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	27.1	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	23.3	Fits
RTX 4070 12GB	12 GB	Q4_K_M	9.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	6.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	3.8	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 CodeLlama 13B Instruct (13B params) fits at each quantization level on NVIDIA L4 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.1 GB	Low	A71
Q3_K_S	3	6.4 GB	Low	A71
NVFP4	4	7.3 GB	Medium	A72
Q4_K_M	4	7.9 GB	Medium	A72
Q5_K_M	5	9.4 GB	High	A73
Q6_K	6	10.7 GB	High	A74
Q8_0Best for your GPU	8	13.9 GB	Very High	A75
F16	16	26.7 GB	Maximum	F0

Get started

Copy-paste commands to run CodeLlama 13B Instruct on your machine.

Run

lms load CodeLlama-13b-Instruct-hf && lms server start

Your hardware

More models your NVIDIA L4 24GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	21.2 tok/s
Qwen 3.5 27B	27B	S	8.9 tok/s
Qwen 3.6 27B	27B	S	6.2 tok/s
Qwen 3.6 35B A3B	35B	A	13.6 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	30.5 tok/s

Frequently asked questions

Can NVIDIA L4 24GB run CodeLlama 13B Instruct?

Yes, NVIDIA L4 24GB can run CodeLlama 13B Instruct with a A grade (Runs with offload). Expected decode speed: 25.8 tok/s.

How much VRAM does CodeLlama 13B Instruct need?

CodeLlama 13B Instruct (13B parameters) requires approximately 23.4 GB of memory with Q4_K_M quantization.

What is the best quantization for CodeLlama 13B Instruct?

The recommended quantization for CodeLlama 13B Instruct is Q4_K_M, which balances quality and memory efficiency.

What speed will CodeLlama 13B Instruct run at on NVIDIA L4 24GB?

On NVIDIA L4 24GB, CodeLlama 13B Instruct achieves approximately 25.8 tokens per second decode speed with a time-to-first-token of 7498ms using Q4_K_M quantization.

Can NVIDIA L4 24GB run CodeLlama 13B Instruct for coding?

For coding workloads, CodeLlama 13B Instruct on NVIDIA L4 24GB receives a A grade with 25.8 tok/s and 16K context.

What context window can CodeLlama 13B Instruct use on NVIDIA L4 24GB?

On NVIDIA L4 24GB, CodeLlama 13B Instruct can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.

What should I upgrade first if CodeLlama 13B Instruct feels slow on NVIDIA L4 24GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for NVIDIA L4 24GB See all hardware for CodeLlama 13B Instruct

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codellama-13b-instruct-on-l4-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: