Can the Mac 16 GB run FLUX.1 Fill [dev]?
Download Q6_K (9.9 GB). With the model's working memory it needs about 12.5 GB, leaving 0.2 GB spare on 12.7 GB. Quality: very close to the original.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-fill-dev-Q6_K.gguf Q6_K · YarvixPA/FLUX.1-Fill-dev-GGUF | models/unet | 9.9 GB | Download → |
| Text encoder | t5-v1_1-xxl-encoder-Q8_0.gguf T5-XXL GGUF Q8_0 · city96/t5-v1_1-xxl-encoder-gguf | models/text_encoders | 5.1 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · comfyanonymous/flux_text_encoders | models/text_encoders | 0.2 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 15.5 GB | |||
Alternatives: T5-XXL FP16 (9.8 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. On a Mac, FP8 text encoders do not load, so a 16-bit one is listed — or a GGUF one, loaded with “CLIPLoader (GGUF)” from the ComfyUI-GGUF nodes. 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 21.5 GB of your 16 GB. On this machine the model, the text encoder, the VAE and the operating system all use the same memory. That is about 5.5 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 FLUX.1 Fill file on 12.7 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.4 GB | 13.7 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · YarvixPA | 12.7 GB | 15.3 GB | 2.6 GB too big | practically identical to the original | Hugging Face → |
| Q6_K ← GGUF · YarvixPA | 9.9 GB | 12.5 GB | fits · 0.2 GB spare | very close to the original | Hugging Face → |
| Q5_K_S GGUF · YarvixPA | 8.3 GB | 10.9 GB | fits · 1.8 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_S GGUF · YarvixPA | 6.8 GB | 9.4 GB | fits · 3.3 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_S GGUF · YarvixPA | 5.2 GB | 7.8 GB | fits · 4.9 GB spare | noticeable loss of detail | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.8 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
T5-XXL: 9.8 GB as 16-bit, 4.9 GB as FP8, 2.9 GB as GGUF Q4_K_M (plus CLIP-L (0.25 GB)). 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 12.7 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
A Mac with 16 GB shares that memory between the CPU and the GPU. On current macOS the GPU may use about 12.7 GB of it by default (older macOS versions: about 11.5 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 16 GB: M1, M1 Pro, M2, M2 Pro, M3, M4, M5, M6 (memory bandwidth 68.25–200 GB/s — the higher, the faster). Everything about Macs and local AI →
Mac 16 GB: 16 GB unified · ~12.7 GB for the GPU · 68.25–200 GB/s · Apple Silicon. Everything that runs on the Mac 16 GB →
05What more VRAM would change
With 16 GB you could run FLUX.1 Fill at 8-bit or better (Q8_0, 12.7 GB) with no offloading: for example on the RTX 5080 16 GB, RTX 5070 Ti 16 GB, RTX 5060 Ti 16 GB.
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.1 Fill on a Mac 16 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does FLUX.1 Fill need?
Around 7.8 GB with the smallest file (Q3_K_S) and 15.3 GB with an 8-bit file (Q8_0), counting working memory and a small system reserve. The full 16-bit file needs about 26.4 GB.
Which FLUX.1 Fill file should I download for the Mac 16 GB?
Q6_K (9.9 GB) from YarvixPA/FLUX.1-Fill-dev-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
Is FP8 faster than GGUF on the Mac 16 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 FLUX.1 Fill on the Mac 16 GB?
About 15.5 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12.7 GB card, 32 GB of system RAM or more is recommended.