HunyuanImage 2.1 on 32 GB of VRAM
Yes. Q8_0 fits on 32 GB with 8.9 GB to spare. Tencent's 17B model that generates natively at 2K. Its GGUF files come from calcuis and need calcuis's own GGUF loader node.
Runs well
Yes, with room to spare.
Q8_0 (19.8 GB) needs about 23.1 GB in use, so 8.9 GB of the 32 GB stays free: room for a larger image, a LoRA or a ControlNet.
Best fileQ8_0
File size19.8 GB
VRAM needed~23.1 GB
System RAM48 GB+
Memory map · 32 GB GPU23.1 GB / 32 GB
016 GB32 GB
Weights Q8_0 · 19.8 GBWorking memory · 2.5 GBReserve · 0.8 GBFree · 8.9 GB
calculated How this is counted.
Got an RTX 40 or 50? Swap Q8_0 for FP8 (17.4 GB): same quality class, computed natively there.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | hunyuanimage2.1-q8_0.gguf Q8_0 · calcuis/hunyuanimage-gguf | models/unet | 19.8 GB | Download → |
| Text encoder | qwen_2.5_vl_7b_fp8_scaled.safetensors Qwen2.5-VL 7B FP8 · Comfy-Org/HunyuanImage_2.1_ComfyUI | models/text_encoders | 9.4 GB | Download → |
| Text encoder | byt5_small_glyphxl_fp16.safetensors ByT5 small Glyph-XL · Comfy-Org/HunyuanImage_2.1_ComfyUI | models/text_encoders | 0.4 GB | Download → |
| VAE | hunyuan_image_2.1_vae_fp16.safetensors HunyuanImage 2.1 VAE · Comfy-Org/HunyuanImage_2.1_ComfyUI | models/vae | 0.8 GB | Download → |
| Total download · keep about the same free on disk | 30.4 GB | |||
Alternatives: Qwen2.5-VL 7B BF16 (16.6 GB). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 30.4 GB of RAM while loaded, 36.4 GB with Windows and ComfyUI. What happens with less. calculated
02Every file, on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 34.9 GB | 38.2 GB | 6.2 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · calcuis | 19.8 GB | 23.1 GB | fits · 8.9 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 17.4 GB | 20.7 GB | fits · 11.3 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · calcuis | 15.7 GB | 19.0 GB | fits · 13.0 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · calcuis | 13.4 GB | 16.7 GB | fits · 15.3 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · calcuis | 11.3 GB | 14.6 GB | fits · 17.4 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · calcuis | 9.8 GB | 13.1 GB | fits · 18.9 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · calcuis | 7.3 GB | 10.6 GB | fits · 21.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2.5 GB of working memory for HunyuanImage 2.1 and a 0.8 GB reserve. Sizes 2026-10-01.