Check my GPU

Video models ·

LTX-2.3

Backbone
18.9B
Native output
1280×704, 121 frames
Default steps
40
License
ltx-2-community
Released
2026-03

How to run it

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

huggingface.co/unsloth/LTX-2.3-GGUF (opens in a new tab)

Original weights · Hugging Face

Full-precision files from Lightricks, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/Lightricks/LTX-2.3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Lightricks. The weights themselves download from Hugging Face.

github.com/Lightricks/LTX-2 (opens in a new tab)

git clone https://github.com/Lightricks/LTX-2

Links checked 6 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 75.4 GB 51.0 GB 25.6 GB Original weights (opens in a new tab)
FP8 44.3 GB 32.1 GB 19.0 GB Original weights (opens in a new tab)
Q8 GGUF 45.6 GB 33.4 GB 19.5 GB GGUF (opens in a new tab)
Q4 GGUF 36.7 GB 24.5 GB 16.4 GB GGUF (opens in a new tab)

Components

Best hardware for LTX-2.3

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7900 XT (launch price $899) at FP8.

Grade · points Hardware Precision Memory Time per output Fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell FP16 75.4 GB / 96.0 GB 4.9 min Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 75.4 GB / 96.0 GB 12.8 min Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) FP16 75.4 GB / 115 GB 13.9 min Runs well
82 ptsGreat (A) · 82 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.2/15, Memory use 15.0/15 Apple M4 Max (128 GB) FP16 75.4 GB / 96.0 GB 39.1 min Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 9.8/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q4 GGUF 24.5 GB / 32.0 GB 7.0 min Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 12.1/15 Apple M2 Ultra (192 GB) FP16 75.4 GB / 144 GB 29.1 min Runs well
80 ptsGreat (A) · 80 of 100 points: Model quality 37.9/45, Memory fit 23.0/25, Speed 4.4/15, Memory use 15.0/15 Apple M4 Max (64 GB) FP8 44.3 GB / 48.0 GB 35.2 min Tight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 37.9/45, Memory fit 23.0/25, Speed 3.5/15, Memory use 15.0/15 Apple M1 Max (64 GB) FP8 44.3 GB / 48.0 GB 53.9 min Tight fit
77 ptsGreat (A) · 77 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.9/15, Memory use 9.1/15 Apple M3 Ultra (256 GB) FP16 75.4 GB / 192 GB 28.2 min Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 38.3/45, Memory fit 18.0/25, Speed 2.9/15, Memory use 15.0/15 Apple M4 Pro (48 GB) Q8 GGUF 33.4 GB / 36.0 GB 79.3 min Tight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.