Best image models for a 32 GB Mac
Which open-weight image models run on a 32 GB Mac. Verdicts come from exact Hugging Face file sizes, model card and app maker statements, and published runs.
- Run
- 9
- Unknown
- 1
- Does not fit
- 0
9 of 10 listed image models run on a 32 GB Mac: Qwen-Image-2.1, FLUX.2 [dev], FLUX.1 [dev], Stable Diffusion 3.5 Large, FLUX 3 Image Klein, FLUX.2 [klein], Krea 2 Turbo, MOSS-Image and SDXL Base 1.0. Highest blind-vote rank among them: Qwen-Image-2.1, #19 of 82 in text to image (Arena, snapshot 2026-10-07). No figure covers Z-Image-Turbo at this size yet.
A 48 GB Mac gets the same verdicts.
License check before commercial use: Qwen-Image-2.1, FLUX.2 [dev], FLUX.1 [dev], Stable Diffusion 3.5 Large, FLUX 3 Image Klein, FLUX.2 [klein], Krea 2 Turbo.
Get the weekly local AI newsletter
The Thursday ModelFit newsletter: new local models and what fits your machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Which image models run on a 32 GB Mac?
10 modelsRuns means a published run on 32 GB or less, or a model card or app maker figure at or below it. Does not fit means the weights the app keeps resident in the smallest complete build are larger than 32 GB. A Mac has one memory pool, so the text encoder cannot move out to a separate system RAM; an app that loads the text encoder and the main model one after the other counts only its largest stage. unknown means no source covers this size yet; it is not a failure.
| Model | Verdict | Why | Quality | App |
|---|---|---|---|---|
| Qwen-Image-2.1Qwen Research License Agreement | Runs · Stated | Stated by the source: 32 GB of unified memory runs it (mlx-serve 8-bit pack).mlx-serve changelog | #19 of 82 in text to image11,441 votes | Diffusers with staged loading, Diffusers, stable-diffusion.cpp |
| FLUX.2 [dev]FLUX Non-Commercial License | Runs · Stated | Stated by the source: 32 GB of unified memory runs it (flux-2-swift-mlx int4 with 4-bit text encoder).flux-2-swift-mlx CLI docs | #38 of 82 in text to image77,988 votes | flux-2-swift-mlx, Diffusers, ComfyUI, stable-diffusion.cpp |
| FLUX.1 [dev]FLUX.1 [dev] Non-Commercial License v1.1.1 | Runs · Published | A dated run on Apple M3 Pro with 18 GB of unified memory, below this 32 GB tier: Draw Things 5-bit, 1024x1024.Draw Things engineering: Metal FlashAttention 2.0 | #78 of 82 in text to image49,221 votes | Diffusers, mflux, ComfyUI |
| Stable Diffusion 3.5 LargeStability AI Community License | Runs · Published | A dated run on Apple M3 Pro with 18 GB of unified memory, below this 32 GB tier: Draw Things 5-bit, 1024x1024.Draw Things engineering: Metal FlashAttention 2.0 | #81 of 82 in text to image23,396 votes | ComfyUI, Rapid-MLX |
| FLUX 3 Image KleinFLUX Kommunity License v1.0 | Runs · Published | A published run on M1 Max · 32 GB used the mflux 4-bit build (20.3 GB download) in mflux.mflux FLUX 3 memory benchmark | No independent score yet | Diffusers, mflux |
| FLUX.2 [klein]Apache 2.0 (4B), FLUX Non-Commercial License (9B) | Runs · Stated | Stated by the source: 24 GB of unified memory runs it, below this 32 GB tier (flux-2-swift-mlx, Klein 9B qint8).flux-2-swift-mlx README | No independent score yet | flux-2-swift-mlx, Diffusers, stable-diffusion.cpp |
| Krea 2 TurboKrea 2 Community License Agreement v.1 | Runs · Published | A published run on M1 Max · 32 GB used the Turbo MLX mixed-4/8 build (19.2 GB download) in ComfyUI-Krea2-MLX.ComfyUI-Krea2-MLX README | No independent score yet | ComfyUI-Krea2-MLX, Diffusers, stable-diffusion.cpp |
| MOSS-ImageApache 2.0 | Runs · Published | A published run on M1 Max · 32 GB used the Original SFT safetensors build (27.2 GB download) in MOSS-Image MPS path.MOSS-Image Apple silicon guide | No independent score yet | MOSS-Image MPS path, stable-diffusion.cpp |
| SDXL Base 1.0CreativeML Open RAIL++-M License | Runs · Published | A dated run on Apple M2 Pro with 16 GB of unified memory, below this 32 GB tier: ComfyUI fp16, 1344x768, 20 steps.ComfyUI issue #948 | No independent score yet | ComfyUI, Rapid-MLX, stable-diffusion.cpp |
| Z-Image-TurboApache 2.0 | unknown | The smallest complete build, Q4_K_M GGUF, is a 12.1 GB download, but no stated figure or published run covers 32 GB of unified memory yet. | #59 of 82 in text to image24,808 votes | Diffusers, mflux, stable-diffusion.cpp |
Quality: blind human votes from Arena (arena.ai), CC BY 4.0, snapshot 2026-10-07. Scores are for the Arena checkpoint, not your local quantized build.
Frequently asked questions
What is the best image model for a 32 GB Mac?
Qwen-Image-2.1 has the highest blind-vote rank among the image models that run on a 32 GB Mac: #19 of 82 in text to image, from 11,441 votes (Arena, snapshot 2026-10-07). FLUX.2 [dev], FLUX.1 [dev], Stable Diffusion 3.5 Large, FLUX 3 Image Klein, FLUX.2 [klein], Krea 2 Turbo, MOSS-Image and SDXL Base 1.0 also run.
Which image models run on a 32 GB Mac?
Qwen-Image-2.1 (32 GB stated by mlx-serve changelog), FLUX.2 [dev] (32 GB stated by flux-2-swift-mlx CLI docs), FLUX.1 [dev] (run on Apple M3 Pro with 18 GB), Stable Diffusion 3.5 Large (run on Apple M3 Pro with 18 GB), FLUX 3 Image Klein (published run on M1 Max · 32 GB), FLUX.2 [klein] (24 GB stated by flux-2-swift-mlx README), Krea 2 Turbo (published run on M1 Max · 32 GB), MOSS-Image (published run on M1 Max · 32 GB) and SDXL Base 1.0 (run on Apple M2 Pro with 16 GB).
Which image models are not confirmed on a 32 GB Mac?
Z-Image-Turbo (Q4_K_M GGUF, 12.1 GB). No stated figure or published run covers this size yet, which is not the same as a failure.