Will It Run AI

Can K EXAONE 236B A23B run on NVIDIA L40S 48GB?

NO — Won't Fit

F0Won't run
Estimated from fit model

K EXAONE 236B A23B needs ~177.6 GB but NVIDIA L40S 48GB only has 48.0 GB. Try a smaller quantization or lighter model.

Runtime: OllamaCapacity: No fitBandwidth: HighStack: BasicBottleneck: Memory capacity
Share:

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) — 177.6 GB, exceeds 48.0 GB available
177.6 GB required48.0 GB available
370% VRAM needed

129.6 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.0 tok/s

TTFT

96800 ms

Safe context

4K

Memory

177.6 GB / 48.0 GB

Offload

70%

Memory breakdown

Weights144.0 GB
KV Cache27.7 GB
Runtime1.2 GB
Headroom4.8 GB

See how fast it feels

With memory offload — actual speed may be lower
See how fast it feelsK EXAONE 236B A23B on NVIDIA L40S 48GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API. When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed. Key benefits of running locally: - Full privacy: your prompts never leave your machine - No per-token cost or rate limits - Works offline once the model is downloaded - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb: Model size Q4 (4-bit) Q8 (8-bit) FP16 7B params ~4.3 GB ~7.5 GB ~14 GB 13B params ~7.9 GB ~13.9 GB ~26 GB 70B params ~42.7 GB ~74.9 GB ~140 GB Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 2.0 tok/s decode · 96.8s TTFT (warm) · 5 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 177.6 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

WorkloadGradeFitDecodeTTFTContext
ChatFToo heavy2.0 tok/s52800 ms4K
CodingFToo heavy2.0 tok/s96800 ms4K
Agentic CodingFToo heavy2.0 tok/s140800 ms4K
ReasoningFToo heavy2.0 tok/s114400 ms4K
RAGFToo heavy2.0 tok/s176000 ms4K

Quantization options

How K EXAONE 236B A23B (236B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
92.0 GB
LowF0
Q3_K_S
3
115.6 GB
LowF0
NVFP4
4
132.2 GB
MediumF0
Q4_K_M
4
144.0 GB
MediumF0
Q5_K_M
5
169.9 GB
HighF0
Q6_K
6
193.5 GB
HighF0
Q8_0
8
252.5 GB
Very HighF0
F16
16
483.8 GB
MaximumF0

升级选项

能流畅运行 K EXAONE 236B A23B 的硬件

NVIDIANVIDIA B200 180GB经济之选
180 GB VRAM (+132)8000 GB/s (+7136)
C
Makes the model fit on the accelerator instead of staying completely out of reach.36.2 tok/s 解码

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

Raises estimated decode speed by about 1710%.

~$30,000 MSRP

NVIDIAB100 192GB最佳性价比
192 GB VRAM (+144)8000 GB/s (+7136)
C
Makes the model fit on the accelerator instead of staying completely out of reach.39.8 tok/s 解码

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.

~$35,000 MSRP

NVIDIANVIDIA GB200 192GBNVIDIA 升级
192 GB VRAM (+144)8000 GB/s (+7136)
C
Makes the model fit on the accelerator instead of staying completely out of reach.39.8 tok/s 解码

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.

~$60,000 MSRP

Frequently asked questions

Can NVIDIA L40S 48GB run K EXAONE 236B A23B?

No, K EXAONE 236B A23B requires more memory than NVIDIA L40S 48GB provides.

How much VRAM does K EXAONE 236B A23B need?

K EXAONE 236B A23B (236B parameters) requires approximately 177.6 GB of memory with Q4_K_M quantization.

What is the best quantization for K EXAONE 236B A23B?

The recommended quantization for K EXAONE 236B A23B is Q4_K_M, which balances quality and memory efficiency.

What speed will K EXAONE 236B A23B run at on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, K EXAONE 236B A23B achieves approximately 2.0 tokens per second decode speed with a time-to-first-token of 96800ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run K EXAONE 236B A23B for coding?

For coding workloads, K EXAONE 236B A23B on NVIDIA L40S 48GB receives a F grade with 2.0 tok/s and 4K context.

What context window can K EXAONE 236B A23B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, K EXAONE 236B A23B can safely use up to 4K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

What should I upgrade first if K EXAONE 236B A23B feels slow on NVIDIA L40S 48GB?

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.

See all results for NVIDIA L40S 48GBSee all hardware for K EXAONE 236B A23B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-lgai-exaone--k-exaone-236b-a23b-gguf-on-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: