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

Best text-to-image models to run locally

A leaderboard of the best text-to-image models you can run on your own computer. Ideogram 4.0 is #1 right now, followed by Qwen-Image-2.1 and ERNIE-Image. Models are ranked on human votes and image generation tests like GenEval. Each model shows the download that fits and the command to run it.

78 models · scores combine 41 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]

Scores use reviewed text to image evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · local only · reset

+ more

set[all sets][LMArena text-to-image · 157][CVTG-2K word accuracy · 3]

Filter the model list while keeping task 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 memory to run

     │                           ● Ideogram 4.0  ∘
  60 ┤ · · ·HiDream-O1-Image ●───┘ · · ·∘· · ∘ ∘ · ∘ ·∘· ∘ ·∘· ∘ · · · · · · · ·∘· · ·∘· ··· ∘ ··· · · · ·∘· ·
     │            ●──────────∘          ∘  ∘     ∘ ∘   ∘        ∘      ∘   ∘∘             ∘
  40 ┤ · ●────────∘· · ·∘· · ∘ · ∘ · ∘ ·∘· ∘ · ∘ ∘ ∘∘· · ∘∘·∘·∘∘ · · ∘ · · ·∘· · · · · · ··· · ··· · · · · · ·
     │   ∘ Dreamlike Photoreal 2.0
     └───────────────────────────────────────────────────────────┬───────────────┬────────┬─────┬────┬───┬───┬
                                                               25GB            50GB     75GB  100GB    150GB

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

#	model	task score↓	where↓	RAM↓	get it	sources
18	Ideogram 4.0 Ideogram	68±2*	local	~6.1GB	how to run ›
19	Qwen-Image-2.1 Alibaba	67±2*	local	~12GB	how to run ›
34	ERNIE-Image Baidu	62±3	local	~17GB	how to run ›
36	Cosmos3-Super-Text2Image NVIDIA	62±2	local	~154GB	how to run ›
37	ERNIE-Image-Turbo Baidu	61±3†	local	~17GB	how to run ›
44	Emu3.5-Image BAAI	60±5*	local	~85GB	how to run ›
48	FLUX.2 [dev] Black Forest Labs	59±1	local	~20GB	how to run ›	+1
52	Krea 2 Turbo Krea	58±2*	local	~20GB	how to run ›
53	Z-Image (Base) Alibaba (Tongyi-MAI)	58±2	local	~10GB	how to run ›
55	HiDream-O1-Image HiDream	58±2	local	~5.3GB	how to run ›
56	HunyuanImage 3.0 Tencent	58±2	local	~49GB	how to run ›	+2
57	Qwen-Image-2512 Alibaba	57±1	local	~22GB	how to run ›
60	Emu3.5 BAAI	56±5*	local	~85GB	how to run ›
62	Z-Image-Turbo Alibaba (Tongyi-MAI)	56±1	local	~7.7GB	how to run ›	+1
63	LLaDA-Image Ant Group	55±3†	local	~22GB	how to run ›
65	HunyuanImage 2.1 Tencent	55±6*	local	~64GB	how to run ›
68	LongCat-Image Meituan	54±4	local	~15GB	how to run ›
69	LLaDA-Image-Turbo Ant Group	53±3†	local	~22GB	how to run ›
70	FLUX.2 [klein] 9B Black Forest Labs	53±2	local	~11GB	how to run ›
71	Qwen-Image Alibaba	53±1	local	~13GB	how to run ›	+5
78	FLUX.2 [klein] 4B Black Forest Labs	49±2	local	~2.9GB	how to run ›
80	GLM-Image Z.ai	49±2	local	~39GB	how to run ›
82	Kandinsky 3 AI Forever	48±10*	local	~32GB	how to run ›
86	Ovis-Image-7B Alibaba (AIDC-AI)	48±7*	local	~12GB	how to run ›
87	FLUX.1 Krea [dev] Black Forest Labs / Krea	48±4*	local	~41GB	how to run ›
88	HiDream-I1-Full HiDream	47±2	local	~76GB	how to run ›
95	UNO ByteDance	44±4*	local	~16GB	how to run ›
97	FLUX.1 [dev] Black Forest Labs	43±1	local	~7.7GB	how to run ›	+3
98	Playground v2 (1024px aesthetic) Playground	43±4*	local	~4.9GB	how to run ›
100	Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)	42±4*	local	~13GB	how to run ›
101	FLUX.1 [schnell] Black Forest Labs	42±3*	local	~7.7GB	how to run ›
102	Show-o2 7B Show Lab, NUS	42±3	local	~23GB	how to run ›
104	Playground v2.5 Playground	41±2	local	~8.8GB	how to run ›	+1
105	Stable Diffusion 3.5 Large Stability AI	41±1	local	~5.4GB	how to run ›	+1
106	BAGEL ByteDance Seed	41±1	local	~12GB	how to run ›	+2
107	FLUX.1 Kontext [dev] Black Forest Labs	40±2*	local	~21GB	how to run ›
108	Stable Diffusion 3.5 Medium Stability AI	40±3*	local	~20GB	how to run ›
109	Show-o2 1.5B-HQ Show Lab, NUS	40±4*	local	~7.9GB	how to run ›
111	OmniGen2 BAAI	40±4*	local	~17GB	how to run ›
112	Stable Cascade Stability AI	40±4*	local	~13GB	how to run ›
113	SDXL-Lightning (4-step UNet) ByteDance	40±4*	local	~4.9GB	how to run ›
114	Stable Diffusion 3 Medium Stability AI	39±2	local	~11GB	how to run ›
116	BLIP3-o 8B Salesforce Research	39±3	local	~41GB	how to run ›
117	Kolors Kuaishou (Kolors team)	38±3	local	~22GB	how to run ›
119	PixArt-α (PixArt-XL-2-1024-MS) PixArt (Huawei Noah's Ark Lab et al.)	38±3	local	~14GB	how to run ›
120	Janus-Pro-7B DeepSeek	37±2	local	~18GB	how to run ›
121	Kandinsky 2.2 AI Forever	37±5*†	local	~12GB	how to run ›
122	SSD-1B Segmind	36±3*	local	~3.3GB	how to run ›
123	Show-o (show-o-demo-512) Show Lab, NUS	36±3*	local	~7.9GB	how to run ›
124	Janus-Pro-1B DeepSeek	36±4	local	~5.5GB	how to run ›
126	Emu3 BAAI	35±2	local	~22GB	how to run ›
127	Stable Diffusion XL 0.9 (base) Stability AI	35±3*	local	~4.9GB	how to run ›
128	SDXL-Turbo Stability AI	35±2	local	~4.9GB	how to run ›
129	Stable Diffusion XL 1.0 Stability AI	35±1	local	~4.9GB	how to run ›	+5
130	IF-XL DeepFloyd	34±2	local	~29GB	how to run ›
131	IF-L DeepFloyd	34±4*	local	~14GB	how to run ›
132	LCM-SDXL latent-consistency	34±3*	local	~8.9GB	how to run ›
133	Dreamlike Photoreal 2.0 Dreamlike.art	34±4*	local	~2.1GB	how to run ›
134	IF-M DeepFloyd	33±4*	local	~14GB	how to run ›
135	Versatile Diffusion v1.0 SHI Labs	33±4*	local	~7.2GB	how to run ›
136	CogView2 THUDM	32±4*	local	~14GB	how to run ›
137	LCM-SSD-1B latent-consistency	32±3*	local	~3.6GB	how to run ›
140	VILA-U 7B (256px) MIT Han Lab / NVIDIA	32±6*	local	~20GB	how to run ›
141	Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis	32±4*	local	~7.5GB	how to run ›
143	Janus-1.3B DeepSeek	31±4	local	~5.5GB	how to run ›
144	VQ-Diffusion (ITHQ) Microsoft	31±4*	local	~4.1GB	how to run ›
146	DALL·E Mega (minDALL-E) DALL·E Mini / minDALL-E	31±3*	local	~8GB	how to run ›
149	Openjourney PromptHero	29±2	local	~2.1GB	how to run ›
150	Stable Diffusion v1.4 CompVis	28±2	local	~2.1GB	how to run ›
151	Stable Diffusion v1.3 CompVis	28±4*	local	~2.1GB	how to run ›
152	Stable Diffusion v1.1 CompVis	27±3	local	~2.1GB	how to run ›
153	Stable Diffusion v1.5 Stability AI	27±2	local	~2.1GB	how to run ›
154	Stable Diffusion v1.2 CompVis	27±3*	local	~2.1GB	how to run ›
155	LCM Dreamshaper v7 SimianLuo (LCM authors)	24±4*	local	~1.7GB	how to run ›
—	Kandinsky 2.1 AI Forever	not scored yet	local	~12GB	how to run ›
—	Mage-Flow Microsoft	not yet calibrated	local	~8.9GB	how to run ›
—	Mage-Flow-Base Microsoft	not yet calibrated	local	~14GB	how to run ›
—	Mage-Flow-Turbo Microsoft	not yet calibrated	local	~8.9GB	how to run ›

+ 84 more don't fit your machine or budget · show them

162 of 162 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