whatmodel.sh · find the best image models you can run

Best image models for a 24GB Mac

A leaderboard of the best image models for a Mac with 24GB of memory. The best one that runs on it right now is Qwen-Image-2.1, followed by Ideogram 4.0 and Z-Image (Base). Models are ranked by one score that combines 73 published benchmarks. Models that run on it show the download that fits and the command to run it.

112 models · scores combine 73 benchmarks · updated 2026-10-11 02:20 UTChow it works · find a leaderboard · benchmark your machine

task[all tasks][text to image][image to image / editing]

Models for 24GB RAM · Apple Silicon → ~16GB fast · reset

+ more

chip[M2][M3][M4][M4 Pro][M5][M5 Pro][M6 (24/32GB)]

set[all sets][LMArena text-to-image · 197][CVTG-2K word accuracy · 3]

Filter the model list while keeping overall scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/image -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/image -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/image -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

ram[8][16][24][32][48][64][96][128][192][256]GB

gpu[apple silicon][graphics card][none]

price[local][$0.001][$0.005][$0.02][$0.1][any]max per image

detecting your OS…

Score vs API price

     │                                                      ◆ GPT Image 2.5 Sunburst
  75 ┤ · · · · · · ··· · · · · · · · · · · · Muse Image·◆───◇· · · · · · · ◇ ◇ · ◇◇· ◇ · · ··· ·◇· · · · ·◇· ·
     │                         Recraft V4.1 Flash ◆─────∘◇    ∘    ◇    ◇∘ ◇ ◇◇ ∘◇  ◇ ◇◇∘ ∘ ∘     ∘    ◇
  50 ┤ · · · · · · ··●───────────────∘─◆─────●────┘· · ·◇· · ◇∘·◇·◇∘ ·∘· ◇ ∘ ◇ · ∘ ·◇∘ ∘◇· ·∘· ·∘·∘· · · · · ·
     │   ●───────────┘        ∘∘                                           ∘
     └──────────────┬───────────────────────────────────┬───────────────────────────────────┬─────────────────
                 $0.001                               $0.01                               $0.1

#	model	score↓	where↓	speed↓	RAM↓	get it	sources

#	model	score↓	where↓	RAM↓	get it	sources
1	GPT Image 2.5 Sunburst OpenAI	92±2	api $0.013/image		fal.ai ↗
2	GPT Image 2.5 Flare OpenAI	88±2	api $0.013/image		fal.ai ↗
3	GPT Image 2 OpenAI	85±1	api $0.053/image		fal.ai ↗	+5
5	Nano Banana 2.1 Google	81±2*	api $0.034/image		ai.google.dev ↗
6	Grok Imagine Image 2.0 SpaceXAI	79±2	api $0.040/image		docs.x.ai ↗
7	Reve 2.1 Reve	78±2	api $0.25/image		fal.ai ↗
8	Muse Image Meta	76±2	api $0.010/image		dev.meta.ai ↗
9	Nano Banana 2 (Gemini 3.1 Flash Image) Google	76±1	api $0.067/image		ai.google.dev ↗	+7
10	Nano Banana Pro (Gemini 3 Pro Image) Google	76±1	api $0.13/image		ai.google.dev ↗	+10
11	Qwen-Image-3.0-Pro Alibaba	75±2	api $0.040/image		www.alibabacloud.com ↗
12	Seedream 5.0 Pro ByteDance Seed	75±2	api $0.050/image		deepinfra.com ↗
13	Reve 2.0 Reve	74±2*	api $0.25/image		fal.ai ↗
14	ChatGPT Image Latest (chatgpt-image-latest) OpenAI	74±4*	api $0.034/image		developers.openai.com ↗
16	Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) Google	73±2	api $0.034/image		ai.google.dev ↗
17	GPT Image 1.5 OpenAI	71±1	api $0.034/image		developers.openai.com ↗	+5
18	Qwen-Image-2.1 · gguf-q4_k + Qwen3-VL 8B q4_k_m (sd.cpp) Alibaba	69±2	local	~12GB	how to run ›
20	Qwen-Image-2.0-Pro (2026-06-22) Alibaba	67±2*	api $0.075/image		www.alibabacloud.com ↗
21	Uni-1.1 Luma AI	67±2*	api $0.040/image		lumalabs.ai ↗
23	Ideogram 4.0 · mlx-q4 Ideogram	66±2*	local	~6.1GB	how to run ›
24	Qwen-Image 2.0 Pro Alibaba	66±3	api $0.075/image		www.alibabacloud.com ↗
26	Grok Imagine Image SpaceXAI (xAI)	66±2	api $0.020/image		docs.x.ai ↗
27	Uni-1.1 Max Luma AI	65±2	api $0.10/image		lumalabs.ai ↗
28	Grok Imagine Image Pro SpaceXAI (xAI)	65±2	api $0.050/image		docs.x.ai ↗
29	Seedream 5.0 Lite ByteDance Seed	65±2	api $0.035/image		docs.byteplus.com ↗	+2
30	Seedream 4.5 ByteDance	64±1	api $0.040/image		docs.byteplus.com ↗	+1
31	Recraft V4.1 Utility Pro Recraft	64±2*	api $0.21/image		www.recraft.ai ↗
32	FLUX.2 [max] Black Forest Labs	64±1	api $0.070/image		docs.bfl.ai ↗
33	Wan 2.7 Image Pro Alibaba	63±2	api $0.075/image		www.alibabacloud.com ↗
36	FLUX.2 [pro] Black Forest Labs	63±2	api $0.030/image		docs.bfl.ai ↗
37	FLUX.2 [flex] Black Forest Labs	62±2	api $0.050/image		docs.bfl.ai ↗
38	HunyuanImage 3.0-Instruct Tencent	62±3*	api $0.090/image		fal.ai ↗
39	Nano Banana (Gemini 2.5 Flash Image) Google	62±1	api $0.039/image		ai.google.dev ↗	+10
40	Wan 2.7 Image Alibaba	62±2	api $0.030/image		www.alibabacloud.com ↗
41	Imagen 4 Ultra Google	61±2	api $0.060/image		cloud.google.com ↗
42	GPT Image 1 OpenAI	61±1	api $0.042/image		developers.openai.com ↗	+9
43	Wan 2.6 Text-to-Image Alibaba	61±3*	api $0.030/image		deepinfra.com ↗
45	Seedream 4.0 ByteDance Seed	61±1	api $0.040/image		deepinfra.com ↗	+5
46	Recraft V4.1 Pro Recraft	61±3*	api $0.21/image		www.recraft.ai ↗
47	ERNIE-Image-Turbo Baidu	61±3†	api $0.010/image	~17GB	fal.ai ↗
49	ERNIE-Image Baidu	60±2	api $0.030/image	~17GB	fal.ai ↗
50	Kling Image O1 Kuaishou (Kling AI)	60±4*	api $0.028/image		kling.ai ↗
51	Krea 2 Medium Krea	60±3*	api $0.030/image		www.krea.ai ↗
52	Imagen 4 Google	59±2	api $0.040/image		cloud.google.com ↗
53	Wan 2.5 Text-to-Image Preview Alibaba	59±3*	api $0.030/image		www.alibabacloud.com ↗
54	Recraft V4 Recraft	59±3*	api $0.040/image		www.recraft.ai ↗
56	Krea 2 Turbo Krea	59±3*	api $0.015/image	~20GB	www.krea.ai ↗
57	GPT Image 1 Mini OpenAI	59±2	api $0.011/image		developers.openai.com ↗
58	Krea 2 Large Krea	59±3*	api $0.060/image		www.krea.ai ↗
59	Qwen-Image-Edit-2509 Alibaba	59±3	api $0.030/image	~26GB	fal.ai ↗
60	HiDream-O1-Image HiDream	58±2	api $0.010/image		fal.ai ↗
61	FLUX.2 [dev] Black Forest Labs	58±1	api $0.046/image	~20GB	developers.cloudflare.com ↗	+8
63	Z-Image (Base) · gguf-q4_k_m + Qwen3 4B q4_k_m (sd.cpp) Alibaba (Tongyi-MAI)	58±2	local	~10GB	how to run ›
64	Wan 2.6 Image Alibaba	58±4*	api $0.030/image		www.alibabacloud.com ↗
65	HunyuanImage 2.1 Tencent	58±2*	api $0.10/image		fal.ai ↗
66	Qwen-Image-Edit-2511 Alibaba	58±2	api $0.030/image	~37GB	fal.ai ↗	+2
67	Recraft V4.1 Flash Recraft	57±3*	api $0.0070/image		www.recraft.ai ↗
68	HunyuanImage 3.0 Tencent	57±2	api $0.080/image		replicate.com ↗	+3
72	LongCat-Image-Edit Meituan	56±2	api $0.15/image		fal.ai ↗
74	P-Image-Edit Pruna	56±4*	api $0.010/image		replicate.com ↗
76	Qwen-Image-2512 Alibaba	56±1	api $0.020/image	~22GB	replicate.com ↗	+1
78	Z-Image-Turbo · gguf-q3_k (+ Qwen3-4B Q4_K_M text encoder) Alibaba (Tongyi-MAI)	55±1	local	~7.7GB	how to run ›	+1
80	Qwen-Image-Edit Alibaba	55±2	api $0.030/image	~27GB	fal.ai ↗	+4
82	FLUX.2 [klein] 9B · gguf-q4_0 + Qwen3 8B q4_k_m (sd.cpp) Black Forest Labs	55±2	local	~14GB	how to run ›
83	FLUX.1 Kontext [max] Black Forest Labs	55±2	api $0.080/image		docs.bfl.ai ↗
85	Qwen-Image Alibaba	54±1	api $0.025/image	~22GB	replicate.com ↗	+8
88	LongCat-Image · gguf-q4_k_m + Qwen2.5-VL q8_0 (sd.cpp) Meituan	53±4	local	~15GB	how to run ›
90	Kling Image 2.1 Kuaishou	53±7*	api $0.014/image		kling.ai ↗
92	Wan 2.5 Image-to-Image Preview Alibaba	53±4*	api $0.030/image		www.alibabacloud.com ↗
93	MiniMax image-01 MiniMax	53±5*	api $0.0035/image		platform.minimax.io ↗
94	Ideogram 3.0 Ideogram	52±2	api $0.060/image		fal.ai ↗
97	FLUX.2 [klein] 4B · gguf-q4_0 + Qwen3 4B q4_k_m (sd.cpp) Black Forest Labs	52±2	local	~6.9GB	how to run ›
98	P-Image Pruna	51±2*	api $0.0050/image		replicate.com ↗
99	Photon Luma AI	51±2	api $0.019/image		fal.ai ↗
100	Recraft V3 Recraft	50±2	api $0.040/image		www.recraft.ai ↗
101	FLUX.1 Kontext [pro] Black Forest Labs	50±2	api $0.040/image		docs.bfl.ai ↗
102	GLM-Image Z.ai	50±2	api $0.015/image		docs.z.ai ↗
104	Runway Gen-4 Image Runway	50±3*	api $0.050/image		docs.dev.runwayml.com ↗
105	Lucid Origin Leonardo.Ai	49±3*	api $0.017/image		replicate.com ↗
113	Ovis-Image-7B · gguf-q4_0 + Ovis 2.5 (sd.cpp) Alibaba (AIDC-AI)	48±7*	local	~12GB	how to run ›
114	FLUX.1 Krea [dev] Black Forest Labs / Krea	47±3	api $0.025/image		replicate.com ↗
116	HiDream-I1-Full HiDream	47±2	api $0.050/image		fal.ai ↗
118	Ideogram 2.0 Ideogram	46±2	api $0.080/image		replicate.com ↗
120	FLUX1.1 [pro] Black Forest Labs	46±2	api $0.040/image		docs.bfl.ai ↗
126	FLUX.1 Kontext [dev] Black Forest Labs	44±1	api $0.025/image	~21GB	replicate.com ↗	+7
127	FLUX.1 [dev] · mlx-4bit Black Forest Labs	44±1	local	~7.7GB	how to run ›	+5
131	Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)	43±4*	api $0.075/image		fal.ai ↗
133	BAGEL ByteDance Seed	42±1	api $0.10/image		fal.ai ↗	+14
135	FLUX.1 [schnell] · mlx-4bit Black Forest Labs	42±2	local	~7.7GB	how to run ›
136	OmniGen2 BAAI	42±2	api $0.15/image		fal.ai ↗	+6
137	Stable Diffusion 3.5 Large Stability AI	42±1	api $0.065/image	~18GB	replicate.com ↗	+4
139	Playground v2 (1024px aesthetic) · fp16 (sd.cpp) Playground	41±4*	local	~8.8GB	how to run ›
141	Stable Diffusion 3.5 Medium Stability AI	41±3	api $0.035/image		platform.stability.ai ↗
148	Stable Diffusion XL 0.9 (base) · q8_0 (sd.cpp --type) Stability AI	40±6*	local	~4.9GB	how to run ›
149	Stable Diffusion 3 Medium · q8_0 (sd.cpp --type) Stability AI	40±2	local	~11GB	how to run ›
153	Janus-Pro-7B DeepSeek	38±2	api $0.0020/image		deepinfra.com ↗
156	SDXL-Lightning (4-step UNet) · fp16 (sd.cpp) ByteDance	37±3*	local	~8.8GB	how to run ›
158	Janus-Pro-1B DeepSeek	36±4	api $0.0005/image		deepinfra.com ↗
161	SSD-1B · fp16 (sd.cpp) Segmind	36±4*	local	~5.9GB	how to run ›
167	Stable Diffusion XL 1.0 · fp16 (sd.cpp) Stability AI	34±1	local	~8.8GB	how to run ›	+8
170	SDXL-Turbo · fp16 (sd.cpp) Stability AI	34±2	local	~8.8GB	how to run ›
178	Dreamlike Photoreal 2.0 · q8_0 (sd.cpp --type) Dreamlike.art	30±3	local	~2.1GB	how to run ›
183	DALL·E Mega (minDALL-E) · fp32 DALL·E Mini / minDALL-E	29±4	local	~8GB	how to run ›
185	Openjourney · q8_0 (sd.cpp --type) PromptHero	28±2	local	~2.1GB	how to run ›
186	Stable Diffusion v1.4 · fp32 CompVis	27±2	local	~8GB	how to run ›
187	Stable Diffusion v1.3 · fp32 CompVis	27±4*	local	~8GB	how to run ›
188	Stable Diffusion v1.1 · fp32 CompVis	26±3	local	~8GB	how to run ›
189	Stable Diffusion v1.2 · fp32 CompVis	26±3*	local	~8GB	how to run ›
191	Stable Diffusion v1.5 · fp32 Stability AI	26±2	local	~8GB	how to run ›	+1
193	LCM Dreamshaper v7 · openvino-fp16 (OpenVINO GenAI) SimianLuo (LCM authors)	23±4*	local	~3GB	how to run ›
—	Mage-Flow · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoft	not yet calibrated	local	~14GB	how to run ›
—	Mage-Flow-Base · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoft	not yet calibrated	local	~14GB	how to run ›
—	Mage-Flow-Turbo · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoft	not yet calibrated	local	~14GB	how to run ›

+ 90 more don't fit your machine or budget · show them

202 of 202 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory