Can the RX 9070 XT 16 GB run LTX-2.5 (22B)?
Not at full quality. The 16-bit and 8-bit files are too big for the RX 9070 XT 16 GB; the largest that fits is Q2_K (8.8 GB).
Take Q2_K (8.8 GB). In use it comes to about 13.6 GB, with 2.4 GB left over on 16 GB. Quality: heavy loss; a last resort. For better quality, Q3_K_M (11.5 GB) also runs, with about 0.3 GB spilling into system RAM - a little slower, still practical.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | LTX-2.5-Distilled-Q2_K.gguf Q2_K · realrebelai/LTX-2.5_GGUFs | models/unet | 8.8 GB | Download → |
| Text encoder | gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors Gemma 4 12B + LTX projection INT8 (convrot) · Lightricks/LTX-2.5 | models/text_encoders | 15.4 GB | Download → |
| VAE | ltx-2.5-video-vae-bf16.safetensors LTX-2.5 video VAE (DiffVAE) BF16 · Lightricks/LTX-2.5 | models/vae | 1.5 GB | Download → |
| Also needed | ltx-2.5-audio-vae-bf16.safetensors LTX-2.5 audio VAE + vocoder BF16 · Lightricks/LTX-2.5 | models/vae | 0.4 GB | Download → |
| Total download · keep about the same free on disk | 26.0 GB | |||
Alternatives: Gemma 4 12B + LTX projection BF16 (26.3 GB). Only for some workflows: LTX-2.5 latent spatial upscaler x2 (1.0 GB, official two-stage template); Gemma 4 E2B INT8 (prompt enhancer, optional) (5.2 GB, only if prompt enhancer enabled). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 26.0 GB of RAM while loaded, 32.0 GB with Windows and ComfyUI. What happens with less. calculated
02Every LTX-2.5 file on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Lightricks | 42.0 GB | 46.8 GB | 30.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · realrebelai | 23.6 GB | 28.4 GB | 12.4 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · realrebelai | 18.7 GB | 23.5 GB | 7.5 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · realrebelai | 16.8 GB | 21.6 GB | 5.6 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · realrebelai | 15.1 GB | 19.9 GB | 3.9 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · realrebelai | 11.5 GB | 16.3 GB | spills 0.3 GB | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · realrebelai | 8.8 GB | 13.6 GB | fits · 2.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 4 GB of working memory for LTX-2.5 and a 0.8 GB reserve. Sizes 2026-10-01.
03The text encoder
At 15.4 GB even the smallest Gemma 4 12B (custom LTX-2.5 build) file is too big for 16 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 26.3 GB, INT8 15.4 GB. Why the encoder does not count against VRAM →
04Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run LTX-2.5 on a RX 9070 XT 16 GB, send your time per image and peak VRAM and it will appear here, credited.
05With more VRAM
With 32 GB you could run LTX-2.5 at 8-bit or better (Q8_0, 23.6 GB) with no offloading: for example on the RTX 5090 32 GB.
06About the RX 9070 XT 16 GB
ComfyUI supports AMD GPUs on Windows officially since v0.7.0 (January 2026), through ROCm. Memory works the same as on NVIDIA, so the fit verdicts apply. Some custom nodes are NVIDIA-only. RX 9000 (RDNA 4) GPUs have FP8 hardware, and ComfyUI computes FP8 natively on them with PyTorch 2.7+ and ROCm 6.4+.
16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4. Everything that runs on it →
07Questions
How much VRAM does LTX-2.5 need?
Around 13.6 GB with the smallest file (Q2_K) and 28.4 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 46.8 GB.
Which LTX-2.5 file should I download for the RX 9070 XT 16 GB?
Q2_K (8.8 GB) from realrebelai/LTX-2.5_GGUFs. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
How much do I need to download for LTX-2.5 on the RX 9070 XT 16 GB?
26.0 GB: LTX-2.5-Distilled-Q2_K.gguf, gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors, ltx-2.5-video-vae-bf16.safetensors, ltx-2.5-audio-vae-bf16.safetensors.