Can Leanstral 119B A6B run on NVIDIA L40S 48GB?

NO — Won't Fit

F0Won't run

○Estimated from fit model

Leanstral 119B A6B needs ~88.6 GB but NVIDIA L40S 48GB only has 48.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: HighStack: OptimizedBottleneck: Memory capacity

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) — 88.6 GB, exceeds 48.0 GB available

88.6 GB required48.0 GB available

185% VRAM needed

40.6 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

4.2 tok/s

TTFT

45666 ms

Safe context

Memory

88.6 GB / 48.0 GB

Offload

50%

Memory breakdown

Weights72.6 GB

KV Cache8.8 GB

Runtime2.4 GB

Headroom4.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsLeanstral 119B A6B on NVIDIA L40S 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: 4.2 tok/s decode · 45.7s TTFT (warm) · 11 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 88.6 GB, but this setup only exposes 48.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	4.7 tok/s	22379 ms	4K
Coding	F	Too heavy	4.2 tok/s	45666 ms	4K
Agentic Coding	F	Too heavy	3.5 tok/s	81060 ms	4K
Reasoning	F	Too heavy	4.2 tok/s	53969 ms	4K
RAG	F	Too heavy	3.5 tok/s	101325 ms	4K

Quantization options

How Leanstral 119B A6B (119B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	F0
Q3_K_S	3	58.3 GB	Low	F0
NVFP4	4

Upgrade options

Hardware that runs Leanstral 119B A6B well

👁 NVIDIA
NVIDIA H200 141GBBudget pick

141 GB VRAM (+93)4800 GB/s (+3936)

Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

👁 NVIDIA
NVIDIA H200 PCIe 141GBBest value

141 GB VRAM (+93)4800 GB/s (+3936)

Makes the model fit on the accelerator instead of staying completely out of reach.88.4 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

👁 NVIDIA
NVIDIA B200 180GBNVIDIA upgrade

180 GB VRAM (+132)8000 GB/s (+7136)

Makes the model fit on the accelerator instead of staying completely out of reach.204.7 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

Frequently asked questions

See all results for NVIDIA L40S 48GB See all hardware for Leanstral 119B A6B

URL: https://willitrunai.com/can-run/leanstral-119b-a6b-on-l40s-48gb

⇱

Can Leanstral 119B A6B run on NVIDIA L40S 48GB?

NO — Won't Fit

Choose the run profile you care about

Memory breakdown

See how fast it feels

What limits this setup

Best improvement path

Performance by workload

Quantization options

Hardware that runs Leanstral 119B A6B well

Frequently asked questions