willitrun·ai

Can K EXAONE 236B A23B run on H100 NVL 188GB?

YES — With Offload

C51Usable
Estimated from fit model

K EXAONE 236B A23B needs ~191.3 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~36 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Balanced
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) — 191.3 GB, 36.4 tok/s, Runs with offload (needs ~2.5 GB host RAM)
191.3 GB required188.0 GB available
102% VRAM needed

3.3 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~2.5 GB host RAM)

Decode

36.4 tok/s

TTFT

5323 ms

Safe context

14K

Memory

191.3 GB / 188.0 GB

Memory breakdown

Weights144.0 GB
KV Cache27.7 GB
Runtime0.9 GB
Headroom18.8 GB

See how fast it feels

See how fast it feelsK EXAONE 236B A23B on H100 NVL 188GB
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: 36.4 tok/s decode · 5.3s TTFT (warm) · 91 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

WorkloadGradeFitDecodeTTFTContext
ChatCTight fit43.9 tok/s2406 ms14K
CodingCRuns with offload (needs ~2.5 GB host RAM)36.4 tok/s5323 ms14K
Agentic CodingDVery compromised (needs ~20.4 GB host RAM)29.1 tok/s9675 ms14K
ReasoningCRuns with offload (needs ~2.5 GB host RAM)36.4 tok/s6291 ms14K
RAGDVery compromised (needs ~20.4 GB host RAM)29.1 tok/s12094 ms14K

Inference speed

K EXAONE 236B A23B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for K EXAONE 236B A23B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~3 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 / MacMemoryQuantSpeed (tok/s)Fits?
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M3.4Heavy offload
NVIDIARTX 5090 32GB
32 GBQ4_K_M2.0Too big
NVIDIARTX 4090 24GB
24 GBQ4_K_M2.0Too big
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M2.0Too big
NVIDIARTX 3090 24GB
24 GBQ4_K_M2.0Too big
NVIDIARTX 4070 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 3060 12GB
12 GBQ4_K_M2.0Too big
NVIDIARTX 4060 8GB
8 GBQ4_K_M2.0Too big
RX 7900 XTX 24GB
24 GBQ4_K_M2.0Too big
MacBook Pro M4 Max 128GB
128 GBQ4_K_M2.0Too big
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M2.0Too big
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M2.0Too big
MacBook Pro M4 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M3 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M1 Max 64GB
64 GBQ4_K_M2.0Too big
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M2.0Too big
NVIDIA2× RTX 4090 24GB
48 GBQ4_K_M2.0Too big
NVIDIA2× RTX 3090 24GB
48 GBQ4_K_M2.0Too big
2× RX 7900 XTX 24GB
48 GBQ4_K_M2.0Too big
NVIDIA4× RTX 3060 12GB
48 GBQ4_K_M2.0Too 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 K EXAONE 236B A23B (236B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
92.0 GB
LowC47
Q3_K_S
3
115.6 GB
LowC48
NVFP4
4
132.2 GB
MediumC48
Q4_K_MBest for your GPU
4
144.0 GB
MediumC48
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

Get started

Copy-paste commands to run K EXAONE 236B A23B on your machine.

Run

lms load hf-lgai-exaone--k-exaone-236b-a23b-gguf && lms server start

Upgrade-Optionen

Hardware, die K EXAONE 236B A23B gut ausführt

NVIDIAB100 192GBGünstige Wahl
192 GB VRAM (+4)8000 GB/s (+200)
C
Raises estimated decode speed by about 28%.46.7 tok/s Dekodierung

Raises estimated decode speed by about 28%.

ca. $35,000 MSRP

NVIDIANVIDIA GB200 192GBBestes Preis-Leistungs-Verhältnis
192 GB VRAM (+4)8000 GB/s (+200)
C
Raises estimated decode speed by about 28%.46.7 tok/s Dekodierung

Raises estimated decode speed by about 28%.

ca. $60,000 MSRP

Frequently asked questions

Can H100 NVL 188GB run K EXAONE 236B A23B?

Yes, H100 NVL 188GB can run K EXAONE 236B A23B with a C grade (Runs with offload (needs ~2.5 GB host RAM)). Expected decode speed: 36.4 tok/s.

How much VRAM does K EXAONE 236B A23B need?

K EXAONE 236B A23B (236B parameters) requires approximately 191.3 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 H100 NVL 188GB?

On H100 NVL 188GB, K EXAONE 236B A23B achieves approximately 36.4 tokens per second decode speed with a time-to-first-token of 5323ms using Q4_K_M quantization.

Can H100 NVL 188GB run K EXAONE 236B A23B for coding?

For coding workloads, K EXAONE 236B A23B on H100 NVL 188GB receives a C grade with 36.4 tok/s and 14K context.

What context window can K EXAONE 236B A23B use on H100 NVL 188GB?

On H100 NVL 188GB, K EXAONE 236B A23B can safely use up to 14K 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 H100 NVL 188GB?

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 H100 NVL 188GBSee 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-h100-nvl-188gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: