Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Ideogram 4 on 6 GB of VRAM

Image model · 9.3BAny 6 GB GPUData 2026-09-25
No
No, not realistically.

Even the smallest file (Q4_1, 6.2 GB (×2, both loaded)) needs about 14.7 GB, far beyond 6 GB. It may start with heavy offloading, but this is not a realistic everyday setup. Pick a smaller model or a GPU with more memory.

Best fileQ4_1
File size6.2 GB ×2
VRAM needed~14.7 GB
System RAM32 GB+
Memory map · 6 GB GPU14.7 GB needed · 8.7 GB over 6 GB
07 GB15 GB
Weights Q4_1 ×2 · 12.4 GBWorking memory · 1.5 GBReserve · 0.8 GBSpills to system RAM · 8.7 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

Worth trying on NVIDIA GPUs: with an up-to-date ComfyUI, Dynamic VRAM (on by default for NVIDIA since March 2026) streams whatever does not fit from system RAM, and ComfyUI's own start-up message recommends native FP8/INT8 files over GGUF, saying they “will be faster even if they are larger than your memory”. So before settling for a heavily compressed GGUF, try the native FP8 file (9.3 GB). The file recommended above is the best one that fits entirely — the safe choice on older ComfyUI versions, AMD and Intel. Comfy blog: Dynamic VRAM →

01What to download

PartFileFolderSize
Modelideogram4-transformer-q4_1.gguf
main model
Q4_1 · molbal/ideogram-4-gguf
models/unet6.2 GBDownload →
Modelideogram4-unconditional_transformer-q4_1.gguf
unconditional model, loaded together with the main one
Q4_1 · molbal/ideogram-4-gguf
models/unet6.2 GBDownload →
Text encoderqwen3vl_8b_fp8_scaled.safetensors
Qwen3-VL 8B FP8 · Comfy-Org/Ideogram-4
models/text_encoders10.6 GBDownload →
VAEflux2-vae.safetensors
FLUX.2 VAE · Comfy-Org/Ideogram-4
models/vae0.3 GBDownload →
Total download · keep about the same free on disk23.3 GB

Alternatives: Qwen3-VL 8B NVFP4 (6.3 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. FP4 files are listed only as alternatives unless the GPU is an RTX 50 (Blackwell). Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 32 GB or more. ComfyUI keeps the model files, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 23.3 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 29.3 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every file, on 6 GB

FileSizeNeededOn this cardQualityDownload
Q8_0
GGUF · molbal
10.1 GB ×222.6 GB16.6 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
9.3 GB ×220.9 GB14.9 GB too bigpractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
9.6 GB ×221.5 GB15.5 GB too bigpractically identical to the originalHugging Face →
Q5_1
GGUF · molbal
7.3 GB ×217.0 GB11.0 GB too bigclose; small differences in fine detailHugging Face →
Q4_1 ←
GGUF · molbal
6.2 GB ×214.7 GB8.7 GB too biggood; some loss in fine detail and textHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file ×2 + 1.5 GB working memory for this model + 0.8 GB kept free for the system. Needs two transformer files loaded together (main + unconditional). GGUF files need the molbal fork of ComfyUI-GGUF. No 16-bit weights were released.

03The text encoder

Qwen3-VL 8B: 10.6 GB as FP8, 6.3 GB as NVFP4. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 6 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.