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

Can the Mac 24 GB run Ideogram 4?

Image model · 9.3B24 GB unified · ~19.6 GB for the GPU · 100–307 GB/s · Apple SiliconData 2026-09-25
Runs
Yes, with a compressed file.

Download Q5_1 (7.3 GB (×2, both loaded)). With the model's working memory it needs about 17.0 GB, leaving 2.6 GB spare on 19.6 GB. Quality: close; small differences in fine detail.

Best fileQ5_1
File size7.3 GB ×2
GPU memory needed~17.0 GB
Shared memory32 / 24 GB
Memory map · Mac 24 GB17.0 GB / 19.6 GB
010 GB20 GB
Weights Q5_1 ×2 · 14.7 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 2.6 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelideogram4-transformer-q5_1.gguf
main model
Q5_1 · molbal/ideogram-4-gguf
models/unet7.3 GBDownload →
Modelideogram4-unconditional_transformer-q5_1.gguf
unconditional model, loaded together with the main one
Q5_1 · molbal/ideogram-4-gguf
models/unet7.3 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 disk25.6 GB

On a Mac, FP8 text encoders do not load, so a 16-bit one is listed. 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.

Shared memory: about 31.6 GB of your 24 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 7.6 GB more than there is. It still runs: while the model works, the system compresses or swaps the idle text encoder, so loading and changing the prompt get slower. A smaller file or text encoder avoids that. calculated

02Every Ideogram 4 file on 19.6 GB

FileSizeNeededOn this cardQualityDownload
Q8_0
GGUF · molbal
10.1 GB ×222.6 GB3.0 GB too bigpractically identical to the originalHugging Face →
Q5_1 ←
GGUF · molbal
7.3 GB ×217.0 GBfits · 2.6 GB spareclose; small differences in fine detailHugging Face →
Q4_1
GGUF · molbal
6.2 GB ×214.7 GBfits · 4.9 GB sparegood; 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. FP8 and INT8 files are left out on a Mac: Apple GPUs cannot compute FP8, so ComfyUI either fails to load them or converts them back to 16-bit, which saves no memory. Use a 16-bit or GGUF file.

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 19.6 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

A Mac with 24 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 19.6 GB of it by default (older macOS versions: about 17.2 GB); that is the figure used here. ComfyUI can go past it, but macOS then starts compressing and swapping memory and everything slows down. ComfyUI runs on Apple GPUs through PyTorch's MPS backend. 16-bit and GGUF files work; FP8 and INT8 files do not save memory on a Mac, so they are skipped. Speed is the catch: even the fastest Macs are several times slower per image than a desktop RTX card. Chips sold with 24 GB: M2, M3, M4, M4 Pro, M5, M5 Pro, M6 (memory bandwidth 100–307 GB/s — the higher, the faster). Everything about Macs and local AI →

Mac 24 GB: 24 GB unified · ~19.6 GB for the GPU · 100–307 GB/s · Apple Silicon. Everything that runs on the Mac 24 GB →

05What more VRAM would change

With 24 GB you could run Ideogram 4 at 8-bit or better (Q8_0, 10.1 GB) with no offloading: for example on the RTX 4090 24 GB, RTX 3090 24 GB, RX 7900 XTX 24 GB.

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Ideogram 4 on a Mac 24 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does Ideogram 4 need?

Around 14.7 GB with the smallest file (Q4_1) and 20.9 GB with an 8-bit file (FP8), counting working memory and a small system reserve.

Which Ideogram 4 file should I download for the Mac 24 GB?

Q5_1 (7.3 GB) from molbal/ideogram-4-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

Is FP8 faster than GGUF on the Mac 24 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for Ideogram 4 on the Mac 24 GB?

About 25.6 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 19.6 GB card, 32 GB of system RAM or more is recommended.