25 GB16GB+ VRAMfp8

ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors

LTX 2.3 Dev FP8 Input Scaled (dash filename, Kijai)

FP8 input-scaled dev model under the alternate `ltx-2-3-…` (dash) filename. Same weights, different name.

Download ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors

Direct HuggingFace download. 25 GB · Free.

Install path: ComfyUI/models/checkpoints/ + ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors

No 16GB GPU? Try ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors online — free generation included

Skip the 25 GB download and ComfyUI setup. Generate a 6-second video using this exact model in your browser, ~30 seconds.

Try this model online — free →

Will this run on my GPU?

Minimum: 16GB VRAM. Headroom up to: 24GB.

GPUVRAMVerdict
RTX 3060 12GB12GBInsufficient VRAM
RTX 4060 Ti / 4070 (16GB)16GBTight fit
RTX 4070 Ti SUPER / 4080 (16GB)16GBTight fit
RTX 3090 (24GB)24GBNo FP8 support
RTX 4090 (24GB)24GBComfortable
RTX 5090 / A6000 (32GB+)32GBComfortable

⚠ FP8 scaled matmul requires RTX 40-series or newer (Ada Lovelace architecture). RTX 30xx cannot run this format — use the MXFP8 block-32 or BF16 variant instead.

Recommendation: Prefer the dotted-filename version unless a specific workflow references this exact name.

How to use ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors

  1. Download the file from HuggingFace.
  2. Place it in ComfyUI/models/checkpoints/ inside your ComfyUI directory.
  3. Restart ComfyUI (or refresh the model list from the menu).
  4. Load a compatible workflow — see below.

Don't want to run this locally? Try ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors online with a free generation — no GPU, no install, ~30 seconds per clip.

Common issues

ComfyUI doesn't see the file after I downloaded it

Make sure the file is in ComfyUI/models/checkpoints/ (not a subfolder). Restart ComfyUI fully — the menu refresh sometimes misses new files. Filename must match exactly: ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors.

I get a CUDA error mentioning fp8 / scaled / matmul

FP8 scaled matmuls require an RTX 40-series GPU or newer (Ada Lovelace architecture). RTX 30-series and older cannot run FP8 weights at native precision. Use the BF16 variant instead, or the MXFP8 block-32 alternative.

CUDA out of memory error when loading the model

ltx-2-3-22b-dev_transformer_only_fp8_input_scaled.safetensors needs ~16GB VRAM minimum. If you're hitting OOM: • Enable Sequential Offloading in ComfyUI settings • Lower the resolution (768×512 instead of 1280×704) — both dimensions must be divisible by 32 • Reduce frame count (65 frames instead of 161) — must be 8n+1 • Use a smaller variant — see Related models below.

Free newsletter

Get notified when LTX 2.3 Dev FP8 Input Scaled (dash filename, Kijai) updates

Occasional updates on what's new in LTX 2.3 — new FP8 quants, LoRAs, IC-LoRA releases — with our hands-on verdict on whether they're worth re-downloading. No fixed cadence.

No spam. Sent occasionally when there's real news. Unsubscribe in one click.

Related models