What GPU do I need to run LGAI-EXAONE/EXAONE-4.0-32B-FP8?

32.0B parameters, published in F8_E4M3. View on Hugging Face

32.0B
Parameters
F8_E4M3
Native precision
Exaone4ForCausalLM
Architecture
text-generation
Pipeline

EXAONE-4.0-32B-FP8 is published by LGAI-EXAONE on Hugging Face, with 16,227 downloads and 21 likes to date. It's a Exaone4ForCausalLM model built for text-generation, published natively in F8_E4M3.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP8 (native)29.8 GB35.8 GBL401$0.759/hr
cheaper alt.RTX 5060 Ti3$0.435/hr
INT4 (quantized)14.9 GB17.9 GBRTX A50001$0.176/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run EXAONE-4.0-32B-FP8 at its published (F8_E4M3) precision: 1× L40, at $0.759/hr per GPU ($0.759/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

EXAONE-4.0-32B-FP8: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Sliding-window attention: windowed layers stop growing at the window, the full-attention layers keep growing. Cached per token: 262,144 bytes at 16-bit while the context is inside the window.

ContextKV cache, one sequence
4K1.0 GB
32K2.8 GB
128K8.8 GB

Computed from the layer, head and window counts in the model's own configuration (LGAI-EXAONE/EXAONE-4.0-32B-FP8), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

EXAONE-4.0-32B-FP8: common questions

Can EXAONE-4.0-32B-FP8 run on a single GPU?

Yes, but not on a desktop card. At FP8 (native) it needs 35.8 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 48.0 GB L40 at $0.759/hr.

Is EXAONE-4.0-32B-FP8 already quantized?

Yes. It is published in FP8, one byte per parameter, so the 35.8 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 17.9 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.

What is the least VRAM EXAONE-4.0-32B-FP8 can run in?

17.9 GB, at INT4 (quantized), which fits a 24 GB card, against 35.8 GB at FP8 (native). That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.

Does quantizing EXAONE-4.0-32B-FP8 lower the GPU bill?

Yes. At FP8 (native) the cheapest live fit is one L40 at $0.759/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More EXAONE 4.0 models

All 3 EXAONE 4.0 models: VRAM and GPU requirements

Lineage

Based on EXAONE-4.0-32B.

Alternatives at this size

Other models for text-generation within about a third of EXAONE-4.0-32B-FP8's 32.0B parameters, from other model lines.

More on EXAONE-4.0-32B-FP8

Related reading: L40 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.