Can the RTX 4090 24 GB run LTX-2.3 (22B)?
Not at full quality. The 16-bit and 8-bit files are too big for the RTX 4090 24 GB; the largest that fits is Q6_K (17.8 GB).
Q6_K (17.8 GB) fits with only 1.4 GB to spare (about 22.6 GB of 24 GB). Quality: very close to the original.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | ltx-2.3-22b-dev-Q6_K.gguf Q6_K · unsloth/LTX-2.3-GGUF | models/unet | 17.8 GB | Download → |
| Text encoder | gemma_3_12B_it_fp8_scaled.safetensors Gemma 3 12B FP8 (scaled) · Comfy-Org/ltx-2 | models/text_encoders | 13.2 GB | Download → |
| VAE | ltx-2.3-22b-dev_video_vae.safetensors LTX-2.3 video VAE · unsloth/LTX-2.3-GGUF | models/vae | 1.5 GB | Download → |
| Also needed | ltx-2.3-22b-dev_audio_vae.safetensors LTX-2.3 audio VAE · unsloth/LTX-2.3-GGUF | models/vae | 0.4 GB | Download → |
| Also needed | ltx-2.3-22b-dev_embeddings_connectors.safetensors LTX-2.3 text embeddings connectors (projection) · unsloth/LTX-2.3-GGUF | models/text_encoders | 2.3 GB | Download → |
| Total download · keep about the same free on disk | 35.1 GB | |||
Alternatives: Gemma 3 12B FP4 mixed (9.4 GB); Gemma 3 12B BF16 (24.4 GB). FP4 files are listed only as alternatives unless the GPU is an RTX 50 (Blackwell). Only for some workflows: LTX-2.3 spatial upscaler x2 1.1 (1.0 GB, official two-stage template). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 35.1 GB of RAM while loaded, 41.1 GB with Windows and ComfyUI. What happens with less. calculated
02Every LTX-2.3 file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit GGUF · unsloth | 42.0 GB | 46.8 GB | 22.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 22.8 GB | 27.6 GB | 3.6 GB too big | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · unsloth | 17.8 GB | 22.6 GB | fits · 1.4 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 16.1 GB | 20.9 GB | fits · 3.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 14.3 GB | 19.1 GB | fits · 4.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 10.8 GB | 15.6 GB | fits · 8.4 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 8.3 GB | 13.1 GB | fits · 10.9 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for LTX-2.3 and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run LTX-2.3 on a RTX 4090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 32 GB you could run LTX-2.3 at 8-bit or better (Q8_0, 22.8 GB) with no offloading: for example on the RTX 5090 32 GB.
What changes from the RTX 4090 24 GB to the RTX 5090 32 GB →
05About the RTX 4090 24 GB
The RTX 4090 24 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on it →
06Questions
How much VRAM does LTX-2.3 need?
Around 13.1 GB with the smallest file (Q2_K) and 27.6 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 46.8 GB.
Which LTX-2.3 file should I download for the RTX 4090 24 GB?
Q6_K (17.8 GB) from unsloth/LTX-2.3-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
How much do I need to download for LTX-2.3 on the RTX 4090 24 GB?
35.1 GB: ltx-2.3-22b-dev-Q6_K.gguf, gemma_3_12B_it_fp8_scaled.safetensors, ltx-2.3-22b-dev_video_vae.safetensors, ltx-2.3-22b-dev_audio_vae.safetensors, ltx-2.3-22b-dev_embeddings_connectors.safetensors.