LTX-Video 13B 0.9.8 (distilled) on Apple M2 Pro (32 GB)

Can the Apple M2 Pro (32 GB) run LTX-Video 13B 0.9.8 (distilled)?

Yes, but slowly (CPU offload)

Slow (CPU offload). At FP8 it needs about 16.1 GB of 21.4 GB usable and takes about 14.5 min per clip.

Best precision: FP8
Memory mode: Sequential CPU offload
Time per clip: 14.5 min
Output: 1216×704, 121 frames, 8 steps

Best app to run it on the Apple M2 Pro (32 GB)

On macOS

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-Video 13B 0.9.8 (distilled)

Original weights · Hugging Face

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

huggingface.co/Lightricks/LTX-Video-0.9.8-13B-distilled (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-Video (opens in a new tab)

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

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, 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 SlowCPU offload: How well it runs on the Apple M2 Pro (32 GB): 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.	30.0 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	12.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	6.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	63.8 / 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 Apple M2 Pro (32 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	20.6 GB	21.4 GB	16.1 min	Sequential CPU offload	Slowtight fit · CPU offload	68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	16.1 GB	21.4 GB	14.5 min	Sequential CPU offload	SlowCPU offload	66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 45 s · Runs well (tight fit)
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) FP16 · 1.9 min · Runs great
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 44 s · Runs great
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX Spark N1X (6144-core GPU) (128 GB) FP16 · 2.2 min · Runs great
66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) FP8 · 5.3 min · Runs well
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) FP16 · 2.1 min · Runs great

Quick answers

How much memory does LTX-Video 13B 0.9.8 (distilled) need on the M2 Pro 32GB?

At FP8 it needs about 16.1 GB. The M2 Pro 32GB has 21.4 GB usable.

How long does LTX-Video 13B 0.9.8 (distilled) take on the M2 Pro 32GB?

About 14.5 min per clip at FP8 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.