EXAONE 4.5 33B hardware requirements

Non-commercial · EXAONE AI Model License 1.2 NCKorean modelChatReasoningVision

About the model

Parameters: 34.35B
Attention: Sliding-window attention
Max context: 262,144 tokens
Released: 2026-04-04
Model card: EXAONE 4.5 33B on Hugging Face

GGUF files

Tracked quantizations of EXAONE 4.5 33B, smallest first
Quant	File size	Quality	Published by
IQ4_XS	18.03 GB	Good balance	Official GGUF · LGAI-EXAONE
Q4_K_Mbaseline	20.05 GB	Good balance	Official GGUF · LGAI-EXAONE
Q6_K	27.13 GB	Near-lossless	Official GGUF · LGAI-EXAONE
Q8_0	35.14 GB	Near-lossless	Official GGUF · LGAI-EXAONE

File sizes do not include the vision projector (mmproj) that image input needs.

Memory needed by quant and context

Weights + f16 KV cache + compute buffer, in GB. Add about 0.6 GB if the GPU also drives your display on Windows.
Quant	4k	8k	16k	32k	64k	128k	256k
IQ4_XS	18.8	19.1	19.8	21.0	23.4	28.3	38.1
Q4_K_M	20.9	21.2	21.8	23.0	25.4	30.3	40.1
Q6_K	27.9	28.2	28.9	30.1	32.5	37.4	47.2
Q8_0	35.9	36.3	36.9	38.1	40.5	45.4	55.2

Which GPUs can run EXAONE 4.5 33B?

How to read the verdicts

Runs great: Fully on the GPU at 20 tok/s or more
Runs well: Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly: 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run: Does not fit, or under 2 tok/s

Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.

Sort

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
Hardware	Verdict	Speed	Quant	Memory	Runs as	Context	Notes	Price
GeForce RTX 5090	Runs great	est. 60.9 tok/s53.6–68.2calibrated estimate ±12%	Q4_K_M	21.8 / 32.0 GB	Full GPU	up to 128k	—	$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX	Runs great	est. 36.4 tok/s32.0–40.7calibrated estimate ±12%	Q4_K_M	21.8 / 24.0 GB	Full GPU	up to 32k	—	$999 launch MSRP
GeForce RTX 3090 Ti	Runs great	est. 34.3 tok/s30.2–38.4calibrated estimate ±12%	Q4_K_M	21.8 / 24.0 GB	Full GPU	up to 32k	—	$1,999 launch MSRP
GeForce RTX 4090	Runs great	est. 34.3 tok/s30.2–38.4calibrated estimate ±12%	Q4_K_M	21.8 / 24.0 GB	Full GPU	up to 32k	—	$2,755 street (as of 2026-08-09)
GeForce RTX 3090	Runs great	est. 31.8 tok/s28.0–35.6calibrated estimate ±12%	Q4_K_M	21.8 / 24.0 GB	Full GPU	up to 16k	—	$1,050 street (as of 2026-08-09)
GeForce RTX 5090 Laptop	Runs great	est. 30.5 tok/s26.8–34.1calibrated estimate ±12%	Q4_K_M	21.8 / 24.0 GB	Full GPU	up to 8k	—	—
Apple M5 Max (40-core GPU) · 48 GB	Runs well	est. 17.9 tok/s14.3–21.5calibrated estimate ±20%	Q4_K_M	21.2 / 33.6 GB	Unified memory	up to 128k	—	—
Apple M3 Ultra · 96 GB	Runs well	est. 17.5 tok/s14.0–21.0calibrated estimate ±20%	Q4_K_M	21.2 / 67.2 GB	Unified memory	up to 128k	—	—
Apple M2 Ultra · 64 GB	Runs well	est. 17.1 tok/s13.7–20.5calibrated estimate ±20%	Q4_K_M	21.2 / 44.8 GB	Unified memory	up to 128k	—	—
Apple M4 Max (40-core GPU) · 48 GB	Runs well	est. 15.9 tok/s12.7–19.1calibrated estimate ±20%	Q4_K_M	21.2 / 33.6 GB	Unified memory	up to 64k	—	—
Radeon RX 7900 XT	Runs well	est. 14.2 tok/s11.4–17.0calibrated estimate ±20%	Q4_K_M	20.0 / 20.0 GB + 1.8 GB RAM	Partial offload	up to 8k	Try IQ4_XS: Runs great	$899 launch MSRP
Apple M5 Max (32-core GPU) · 36 GB	Runs well	est. 13.4 tok/s10.7–16.1calibrated estimate ±20%	Q4_K_M	21.2 / 25.2 GB	Unified memory	up to 32k	—	—
Apple M4 Max (32-core GPU) · 36 GB	Runs slowly	est. 11.9 tok/s9.6–14.3calibrated estimate ±20%	Q4_K_M	21.2 / 25.2 GB	Unified memory	up to 32k	Try IQ4_XS: Runs well	—
Apple M5 Pro · 48 GB	Runs slowly	est. 8.9 tok/s7.2–10.7calibrated estimate ±20%	Q4_K_M	21.2 / 33.6 GB	Unified memory	up to 128k	—	—
Ryzen AI Max+ 395 (Strix Halo) · 32 GB	Runs slowly	est. 8.1 tok/s6.5–9.7calibrated estimate ±20%	Q4_K_M	21.2 / 22.4 GB	Unified memory	up to 16k	—	$1,999 launch MSRP
Apple M4 Pro · 48 GB	Runs slowly	est. 8.0 tok/s6.4–9.5calibrated estimate ±20%	Q4_K_M	21.2 / 33.6 GB	Unified memory	up to 128k	—	—
GeForce RTX 5080	Runs slowly	est. 6.5 tok/s5.2–7.8calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$1,256 street (as of 2026-08-09)
GeForce RTX 5070 Ti	Runs slowly	est. 6.4 tok/s5.1–7.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop	Runs slowly	est. 6.4 tok/s5.1–7.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	—
GeForce RTX 4080 Super	Runs slowly	est. 6.2 tok/s5.0–7.5calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$999 launch MSRP
Radeon RX 9070	Runs slowly	est. 6.2 tok/s5.0–7.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$639 street (as of 2026-08-09)
Radeon RX 9070 XT	Runs slowly	est. 6.2 tok/s5.0–7.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$689 street (as of 2026-08-09)
GeForce RTX 4080	Runs slowly	est. 6.2 tok/s5.0–7.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$1,199 launch MSRP
Radeon RX 7800 XT	Runs slowly	est. 6.2 tok/s4.9–7.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$499 launch MSRP
GeForce RTX 4070 Ti Super	Runs slowly	est. 6.1 tok/s4.9–7.4calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$799 launch MSRP
GeForce RTX 4090 Laptop	Runs slowly	est. 5.9 tok/s4.7–7.1calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	—
GeForce RTX 5060 Ti 16GB	Runs slowly	est. 5.6 tok/s4.5–6.7calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$569 street (as of 2026-08-09)
NVIDIA DGX Spark · 128 GB	Runs slowly	est. 5.3 tok/s4.2–6.4calibrated estimate ±20%	Q4_K_M	21.2 / 89.6 GB	Unified memory	up to 128k	—	$3,999 launch MSRP
Radeon RX 9060 XT 16GB	Runs slowly	est. 5.3 tok/s4.2–6.3calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$449 street (as of 2026-08-09)
GeForce RTX 4060 Ti 16GB	Runs slowly	est. 4.9 tok/s3.9–5.9calibrated estimate ±20%	Q4_K_M	16.0 / 16.0 GB + 5.8 GB RAM	Partial offload	up to 64k	—	$499 launch MSRP
Apple M5 · 32 GB	Runs slowly	est. 4.5 tok/s3.6–5.4calibrated estimate ±20%	Q4_K_M	21.2 / 22.4 GB	Unified memory	up to 16k	—	—
GeForce RTX 3080 12GB	Runs slowly	est. 4.2 tok/s3.3–5.0calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$799 launch MSRP
GeForce RTX 5070	Runs slowly	est. 4.1 tok/s3.2–4.9calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop	Runs slowly	est. 4.1 tok/s3.2–4.9calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	—
GeForce RTX 4070	Runs slowly	est. 3.9 tok/s3.2–4.7calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$599 launch MSRP
GeForce RTX 4070 Super	Runs slowly	est. 3.9 tok/s3.2–4.7calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$599 launch MSRP
GeForce RTX 4080 Laptop	Runs slowly	est. 3.9 tok/s3.1–4.6calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	—
Intel Arc B580	Runs slowly	est. 3.8 tok/s3.0–4.6calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB	Runs slowly	est. 3.8 tok/s3.0–4.5calibrated estimate ±20%	Q4_K_M	12.0 / 12.0 GB + 9.8 GB RAM	Partial offload	up to 32k	—	$250 street (as of 2026-08-09)
GeForce RTX 2080 Ti	Runs slowly	est. 3.7 tok/s3.0–4.5calibrated estimate ±20%	Q4_K_M	11.0 / 11.0 GB + 10.8 GB RAM	Partial offload	up to 32k	—	$999 launch MSRP
GeForce GTX 1080 Ti	Runs slowly	est. 3.6 tok/s2.5–4.7theoretical estimate ±30%	Q4_K_M	11.0 / 11.0 GB + 10.8 GB RAM	Partial offload	up to 16k	—	$699 launch MSRP
GeForce RTX 3080 10GB	Runs slowly	est. 3.5 tok/s2.8–4.2calibrated estimate ±20%	Q4_K_M	10.0 / 10.0 GB + 11.8 GB RAM	Partial offload	up to 16k	—	$699 launch MSRP
Apple M4 · 32 GB	Runs slowly	est. 3.5 tok/s2.8–4.2calibrated estimate ±20%	Q4_K_M	21.2 / 22.4 GB	Unified memory	up to 16k	—	—
GeForce RTX 3070	Won't runTry IQ4_XS: Runs slowly	est. 3.4 tok/s2.8–4.1calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$499 launch MSRP
GeForce RTX 5060	Won't runTry IQ4_XS: Runs slowly	est. 3.4 tok/s2.8–4.1calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB	Won't runTry IQ4_XS: Runs slowly	est. 3.4 tok/s2.8–4.1calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$429 street (as of 2026-08-09)
GeForce RTX 4060 Ti 8GB	Won't runTry IQ4_XS: Runs slowly	est. 3.3 tok/s2.6–4.0calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$399 launch MSRP
GeForce RTX 4060	Won't runTry IQ4_XS: Runs slowly	est. 3.3 tok/s2.6–3.9calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$299 launch MSRP
GeForce RTX 4060 Laptop	Won't runTry IQ4_XS: Runs slowly	est. 3.3 tok/s2.6–3.9calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	—
GeForce RTX 4070 Laptop	Won't runTry IQ4_XS: Runs slowly	est. 3.3 tok/s2.6–3.9calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	—
GeForce RTX 3050 8GB	Won't runTry IQ4_XS: Runs slowly	est. 3.2 tok/s2.6–3.9calibrated estimate ±20%	IQ4_XS	8.0 / 8.0 GB + 11.7 GB RAM	Partial offload	up to 16k	—	$249 launch MSRP
DDR5-6000 dual-channel CPU · 96 GB	Won't run	est. 2.3 tok/s1.9–2.8calibrated estimate ±20%	Q4_K_M	20.6 GB RAM	CPU only	—	Fits, but too slow to use	—
DDR5-5600 dual-channel CPU · 96 GB	Won't run	est. 2.2 tok/s1.7–2.6calibrated estimate ±20%	Q4_K_M	20.6 GB RAM	CPU only	—	Fits, but too slow to use	—
DDR4-3200 dual-channel CPU · 64 GB	Won't run	est. 1.2 tok/s1.0–1.5calibrated estimate ±20%	Q4_K_M	20.6 GB RAM	CPU only	—	Fits, but too slow to use	—

Reasoning models spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s).

Cheapest GPUs that run it

Runs greatGeForce RTX 3090$1,050 street (as of 2026-08-09), est. 31.8 tok/s (28.0–35.6, calibrated estimate ±12%).

Measured results for EXAONE 4.5 33B

No public measurements for this model yet.

Frequently asked questions

How much VRAM does EXAONE 4.5 33B need?

At Q4_K_M the weights are 20.05 GB; with 8k context the total is about 21.2 GB (KV cache 0.5 GB, compute buffer 0.6 GB). The smallest tracked file (IQ4_XS) needs about 19.1 GB.

What is the cheapest GPU that runs EXAONE 4.5 33B well?

Cheapest that runs it great: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 31.8 tok/s (28.0–35.6, calibrated estimate ±12%).

Can EXAONE 4.5 33B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Won't run, est. 2.9 tok/s (2.3–3.4, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs slowly, est. 5.6 tok/s (4.5–6.7, calibrated estimate ±20%); GeForce RTX 3090 — Runs great, est. 31.8 tok/s (28.0–35.6, calibrated estimate ±12%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.