Model reference · open weights
LTX-2.3-quants is an open-weight video model from Hippotes, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
14/04: uploaded fp8mixed an nvfp4mixed of LTX-2.3-distilled-1.1 16/03: Lightricks released an official dev-nvfp4 and distilled-fp8 09/03: all formats of both dev & distilled in nvfp4, nvfp4mixed, fp8, and fp8mixed done. 07/03: ⚠️ make sure your torch (=2.10) & cuda (=13.0) are up to date, otherwise you won't see a speed boost using nvfp4, may even be slower ⚠️ 05/03: Lightricks released an official dev-fp8, probably better to use it instead of mine. Various formats of LTX-2.3, all created from official BF16 versions. Made with Silveroxides/converttoquant script: - fp8mixed - fp8 - nvfp4mixed - nvfp4 - non-calibrated / nc: direct conversion without SVD optimization - mixed: keep some weights in native format (embeddings, norm, bias, etc), same exclusion strategy as Lightricks run time config: Windows 11, Nvidia 5090, torch2.10+cu130, SageAttention2.2 - 8 steps, CFG 1 - default sampler/scheduler - 960 x 544p, 121 frames, 24 fps - x2 spatial upscale - 4 refining steps Hot run, prompt already processed. Smaller formats look a bit "fuzzy" around the edges in the outputs, but motion, audio, and lighting are still looking good.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Hippotes |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | diffusers |
| Based on | Lightricks/LTX-2.3 |
| Released | 2026-03-05 |
| Popularity | 14k downloads / month |
| Likes | 36 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| LTX-2.3-quants | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys ltx-2-3-quants for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ltx-2-3-quants below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"ltx-2-3-quants","prompt":"a drone shot over a forest"}'
Details
Tags
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore