LTX-2.5 (22B, video + audio) on NVIDIA H100 80GB SXM

Can the NVIDIA H100 80GB SXM run LTX-2.5 (22B, video + audio)?

Yes, it runs great

Runs great. At Q8 GGUF it needs about 49.8 GB of 80.0 GB usable and takes about 73 s per clip.

Best precision: Q8 GGUF
Memory mode: Everything on GPU
Time per clip: 73 s
Output: 1280×704, 121 frames, 8 steps

Best app to run it on the NVIDIA H100 80GB SXM

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

On Windows

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download LTX-2.5 (22B, video + audio)

Recommended for the NVIDIA H100 80GB SXM: q8_gguf. Every other precision has its own download link in the table below.

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.

Download the q8_gguf (Q8_0) file (opens in a new tab)

huggingface.co/unsloth/LTX-2.5-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-2.5 (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8 GGUF, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA H100 80GB SXM: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	39.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	14.4 / 15
Match score	93.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the NVIDIA H100 80GB SXM

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	56.2 GB	80.0 GB	67 s	Text encoder offloaded	Runs greatencoder in RAM	88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	48.3 GB	80.0 GB	57 s	Everything on GPU	Runs great	86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	49.8 GB	80.0 GB	73 s	Everything on GPU	Runs great	87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	39.9 GB	80.0 GB	76 s	Everything on GPU	Runs great	81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) FP16 · 3.2 min · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) FP16 · 3.3 min · Runs great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8 GGUF · 77 s · Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) FP8 · 2.6 min · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) FP16 · 6.6 min · Runs well
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4 GGUF · 1.6 min · Runs great (encoder in RAM)

Quick answers

How much memory does LTX-2.5 (22B, video + audio) need on the NVIDIA H100 80GB SXM?

At Q8 GGUF it needs about 49.8 GB. The NVIDIA H100 80GB SXM has 80.0 GB usable.

How long does LTX-2.5 (22B, video + audio) take on the NVIDIA H100 80GB SXM?

About 73 s per clip at Q8 GGUF and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

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.