Can the AMD Radeon PRO W7800 32GB run LTX-2.3?

78 pts

Yes, it runs well

Runs well. At Q4 GGUF it needs about 24.5 GB of 32.0 GB usable, with an estimated speed of 11.8 min.

Best precision: Q4 GGUF
Memory mode: Text encoder offloaded
Time per clip: 11.8 min
Output: 1280×704, 121 frames, 40 steps

Download LTX-2.3

Recommended for the AMD Radeon PRO W7800 32GB: q4_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 q4_gguf (Q4_K_S) file (opens in a new tab)

huggingface.co/unsloth/LTX-2.3-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-2.3 (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-2 (opens in a new tab)

git clone https://github.com/Lightricks/LTX-2

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the A grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	36.0 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	20.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.6 / 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
Total	78.6 / 100	78 ptsGreat (A) · 78 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 7.6/15, Memory use 15.0/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every precision on the AMD Radeon PRO W7800 32GB

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	25.6 GB	32.0 GB	12.1 min	Sequential CPU offload	Runs well	73 ptsGreat (A) · 73 of 100 points: Model quality 38.7/45, Memory fit 12.0/25, Speed 7.5/15, Memory use 15.0/15	Original weights (opens in a new tab)
`FP8`	19.0 GB	32.0 GB	10.9 min	Sequential CPU offload	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 37.9/45, Memory fit 12.0/25, Speed 7.9/15, Memory use 13.7/15	Original weights (opens in a new tab)
`Q8 GGUF`	19.5 GB	32.0 GB	14.0 min	Sequential CPU offload	Runs well	71 ptsGood (B) · 71 of 100 points: Model quality 38.3/45, Memory fit 12.0/25, Speed 7.0/15, Memory use 14.0/15	GGUF (opens in a new tab)
`Q4 GGUF`	24.5 GB	32.0 GB	11.8 min	Text encoder offloaded	Runs well	78 ptsGreat (A) · 78 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 7.6/15, Memory use 15.0/15	GGUF (opens in a new tab)

Other hardware that runs it

90 ptsExcellent (S) · 90 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell FP16 · 4.9 min
85 ptsExcellent (S) · 85 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 12.8 min
85 ptsExcellent (S) · 85 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 7.0/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) FP16 · 13.9 min
82 ptsGreat (A) · 82 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.2/15, Memory use 15.0/15 Apple M4 Max (128 GB) FP16 · 39.1 min
80 ptsGreat (A) · 80 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 9.8/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q4 GGUF · 7.0 min
80 ptsGreat (A) · 80 of 100 points: Model quality 38.7/45, Memory fit 25.0/25, Speed 4.8/15, Memory use 12.1/15 Apple M2 Ultra (192 GB) FP16 · 29.1 min

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.