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

Best image models for a 96GB Mac

A leaderboard of the best image models for a Mac with 96GB of memory. The best one that runs on it right now is Qwen-Image-2.1, followed by Ideogram 4.0 and ERNIE-Image-Turbo. 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.

114 models · scores combine 73 benchmarks · updated how it works · find a leaderboard · benchmark your machine
Models for 96GB RAM · Apple Silicon → ~72GB fast · reset
+ more
$ terminal

detecting your OS…

Score vs API price

#modelscore↓where↓speed↓RAM↓get itsources
1GPT Image 2.5 Sunburst OpenAI92±2api $0.013/imagefal.ai ↗LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)
2GPT Image 2.5 Flare OpenAI88±2api $0.013/imagefal.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)
3GPT Image 2 OpenAI85±1api $0.053/imagefal.ai ↗LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1InfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)PaintBench: Deterministic Evaluation of Precise Visual Editing (arXiv:2606.00188v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)+5
5Nano Banana 2.1 Google81±2*api $0.034/imageai.google.dev ↗LMArena leaderboard dataset
6Grok Imagine Image 2.0 SpaceXAI79±2api $0.040/imagedocs.x.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
7Reve 2.1 Reve78±2api $0.25/imagefal.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
8Muse Image Meta76±2api $0.010/imagedev.meta.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
9Nano Banana 2 (Gemini 3.1 Flash Image) Google76±1api $0.067/imageai.google.dev ↗LMArena leaderboard datasetInfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1GenExam leaderboard (OpenGVLab/GenExam README, relaxed score)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings+7
10Nano Banana Pro (Gemini 3 Pro Image) Google76±1api $0.13/imageai.google.dev ↗LMArena leaderboard datasetInfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)+10
11Qwen-Image-3.0-Pro Alibaba75±2api $0.040/imagewww.alibabacloud.com ↗LMArena leaderboard datasetGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)
12Seedream 5.0 Pro ByteDance Seed75±2api $0.050/imagedeepinfra.com ↗LMArena leaderboard datasetGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)
13Reve 2.0 Reve74±2*api $0.25/imagefal.ai ↗LMArena leaderboard dataset
14ChatGPT Image Latest (chatgpt-image-latest) OpenAI74±4*api $0.034/imagedevelopers.openai.com ↗LMArena leaderboard dataset
16Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) Google73±2api $0.034/imageai.google.dev ↗LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1
17GPT Image 1.5 OpenAI71±1api $0.034/imagedevelopers.openai.com ↗LMArena leaderboard datasetGenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)GEBench: Benchmarking Image Generation Models as GUI EnvironmentsUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsGEditBench v2: A Human-Aligned Benchmark for General Image Editing+5
18Qwen-Image-2.1 · int8 convrot + Qwen3-VL 8B q4_k_m (sd.cpp) Alibaba69±2local~16GBhow to run › LMArena leaderboard datasetGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)
20Qwen-Image-2.0-Pro (2026-06-22) Alibaba67±2*api $0.075/imagewww.alibabacloud.com ↗LMArena leaderboard dataset
21Uni-1.1 Luma AI67±2*api $0.040/imagelumalabs.ai ↗LMArena leaderboard dataset
23Ideogram 4.0 · fp8 + Qwen3-VL 8B q4_k_m (sd.cpp) Ideogram66±2*local~29GBhow to run › LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
24Qwen-Image 2.0 Pro Alibaba66±3api $0.075/imagewww.alibabacloud.com ↗ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsFaithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models (FEPBench)Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
26Grok Imagine Image SpaceXAI (xAI)66±2api $0.020/imagedocs.x.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
27Uni-1.1 Max Luma AI65±2api $0.10/imagelumalabs.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
28Grok Imagine Image Pro SpaceXAI (xAI)65±2api $0.050/imagedocs.x.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsTECCI: Tricky Edits of Collected and Curated Images
29Seedream 5.0 Lite ByteDance Seed65±2api $0.035/imagedocs.byteplus.com ↗LMArena leaderboard datasetInfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)ChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal ConsistencyRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsFaithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models (FEPBench)+2
30Seedream 4.5 ByteDance64±1api $0.040/imagedocs.byteplus.com ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetEdit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingGEBench: Benchmarking Image Generation Models as GUI EnvironmentsRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsGEditBench v2: A Human-Aligned Benchmark for General Image Editing+1
31Recraft V4.1 Utility Pro Recraft64±2*api $0.21/imagewww.recraft.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
32FLUX.2 [max] Black Forest Labs64±1api $0.070/imagedocs.bfl.ai ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsEdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing (arXiv:2509.13399v3)Qwen-Image-Bench: From Generation to Creation in Text-to-Image EvaluationKnowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation (arXiv:2604.22302v1)
33Wan 2.7 Image Pro Alibaba63±2api $0.075/imagewww.alibabacloud.com ↗LMArena leaderboard datasetChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
36FLUX.2 [pro] Black Forest Labs63±2api $0.030/imagedocs.bfl.ai ↗LMArena leaderboard datasetCan Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal ConsistencyGEBench: Benchmarking Image Generation Models as GUI EnvironmentsRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsQwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
37FLUX.2 [flex] Black Forest Labs62±2api $0.050/imagedocs.bfl.ai ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
38HunyuanImage 3.0-Instruct Tencent62±3*api $0.090/imagefal.ai ↗LMArena leaderboard datasetInfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)
39Nano Banana (Gemini 2.5 Flash Image) Google62±1api $0.039/imageai.google.dev ↗LMArena leaderboard datasetServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)Meituan LongCat — LongCat-Image technical reportGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)InfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)+10
40Wan 2.7 Image Alibaba62±2api $0.030/imagewww.alibabacloud.com ↗LMArena leaderboard datasetEdit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
41Imagen 4 Ultra Google61±2api $0.060/imagecloud.google.com ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsQwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
42GPT Image 1 OpenAI61±1api $0.042/imagedevelopers.openai.com ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)Meituan LongCat — LongCat-Image technical reportMMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)+9
43Wan 2.6 Text-to-Image Alibaba61±3*api $0.030/imagedeepinfra.com ↗LMArena leaderboard dataset
45Seedream 4.0 ByteDance Seed61±1api $0.040/imagedeepinfra.com ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)Meituan LongCat — LongCat-Image technical reportGEBench: Benchmarking Image Generation Models as GUI EnvironmentsUnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits+5
46Recraft V4.1 Pro Recraft61±3*api $0.21/imagewww.recraft.ai ↗LMArena leaderboard dataset
47ERNIE-Image-Turbo · bf16 + Ministral 3B (sd.cpp) Baidu61±3†local~29GBhow to run › ERNIE-Image model repository evaluation tables
49ERNIE-Image · gguf-ud-q4_k_m + Ministral 3B (sd.cpp, all files in memory) Baidu60±2local~17GBhow to run › ERNIE-Image model repository evaluation tablesQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
50Kling Image O1 Kuaishou (Kling AI)60±4*api $0.028/imagekling.ai ↗LMArena leaderboard dataset
51Krea 2 Medium Krea60±3*api $0.030/imagewww.krea.ai ↗LMArena leaderboard dataset
52Imagen 4 Google59±2api $0.040/imagecloud.google.com ↗LMArena leaderboard datasetServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsQwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
53Wan 2.5 Text-to-Image Preview Alibaba59±3*api $0.030/imagewww.alibabacloud.com ↗LMArena leaderboard dataset
54Recraft V4 Recraft59±3*api $0.040/imagewww.recraft.ai ↗LMArena leaderboard dataset
56Krea 2 Turbo · gguf-q8_0 + Qwen3-VL 4B q4_k_m (sd.cpp) Krea59±3*local~20GBhow to run › LMArena leaderboard dataset
57GPT Image 1 Mini OpenAI59±2api $0.011/imagedevelopers.openai.com ↗LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)
58Krea 2 Large Krea59±3*api $0.060/imagewww.krea.ai ↗LMArena leaderboard dataset
59Qwen-Image-Edit-2509 · gguf-q4_k_s + Qwen2.5-VL q8_0 (sd.cpp) Alibaba59±3local~26GBhow to run › Meituan LongCat — LongCat-Image technical reportGEditBench v2: A Human-Aligned Benchmark for General Image EditingHP-Edit: A Human-Preference Post-Training Framework for Image Editing (arXiv:2604.19406v1)ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? (arXiv:2603.25823v1)BAAI — OmniGen2 technical report
60HiDream-O1-Image HiDream58±2api $0.010/imagefal.ai ↗LMArena leaderboard datasetQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsHiDream-ai/HiDream-O1-Image repository README results
61FLUX.2 [dev] · gguf-q4_k_s + Mistral Small 3.2 q4_k_m (sd.cpp) Black Forest Labs58±1local~41GBhow to run › GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)TIIF-Bench: How Does Your T2I Model Follow Your Instructions? (arXiv v3)+8
63Z-Image (Base) · bf16 + Qwen3 4B bf16 (sd.cpp) Alibaba (Tongyi-MAI)58±2local~25GBhow to run › Tongyi-MAI (Alibaba) — Z-Image technical reportQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)
64Wan 2.6 Image Alibaba58±4*api $0.030/imagewww.alibabacloud.com ↗LMArena leaderboard dataset
65HunyuanImage 2.1 Tencent58±2*api $0.10/imagefal.ai ↗Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency
66Qwen-Image-Edit-2511 · gguf-q4_k_m + Qwen2.5-VL bf16 (sd.cpp) Alibaba58±2local~37GBhow to run › Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingLMArena leaderboard datasetChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)InfoEdit: Probing Global Layout Reasoning in Infographic Editing (arXiv:2609.33286v1)GEditBench v2: A Human-Aligned Benchmark for General Image EditingMultiTextEdit: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing (arXiv:2605.08163v2), Table 3+2
67Recraft V4.1 Flash Recraft57±3*api $0.0070/imagewww.recraft.ai ↗LMArena leaderboard dataset
68HunyuanImage 3.0 Tencent57±2api $0.080/imagereplicate.com ↗LMArena leaderboard datasetGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsFaithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models (FEPBench)+3
72LongCat-Image-Edit Meituan56±2api $0.15/imagefal.ai ↗Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingMeituan LongCat — LongCat-Image technical reportChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)GEditBench v2: A Human-Aligned Benchmark for General Image EditingPaintBench: Deterministic Evaluation of Precise Visual Editing (arXiv:2606.00188v1)ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? (arXiv:2603.25823v1)
74P-Image-Edit Pruna56±4*api $0.010/imagereplicate.com ↗LMArena leaderboard dataset
76Qwen-Image-2512 · gguf-q4_k_m (Unsloth) + Qwen2.5-VL Q4_K_XL Alibaba56±1local~22GBhow to run › GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)LMArena leaderboard datasetVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency+1
78Z-Image-Turbo · gguf-q3_k (+ Qwen3-4B Q4_K_M text encoder) Alibaba (Tongyi-MAI)55±1local~7.7GBhow to run › Tongyi-MAI (Alibaba) — Z-Image technical reportLMArena leaderboard datasetQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Cosmos 3: Omnimodal World Models for Physical AI (arXiv:2606.02800v4)Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency+1
79LLaDA-Image · f16 + LLaDA2 text encoder q8_0 (sd.cpp) Ant Group55±3†local~39GBhow to run › LLaDA-Image: Building Strong Image Generators with Fully Open Training RecipesUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)
80Qwen-Image-Edit · gguf-q8_0 + Qwen2.5-VL bf16 (sd.cpp) Alibaba55±2local~47GBhow to run › Meituan LongCat — LongCat-Image technical reportLMArena leaderboard datasetChartSync: A Benchmark for Visuo-Logical Cascading Chart Editing (arXiv:2607.10301v1)GEBench: Benchmarking Image Generation Models as GUI EnvironmentsUnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched EditsHP-Edit: A Human-Preference Post-Training Framework for Image Editing (arXiv:2604.19406v1)+4
82FLUX.2 [klein] 9B · gguf-q4_0 + Qwen3 8B q4_k_m (sd.cpp) Black Forest Labs55±2local~14GBhow to run › LMArena leaderboard datasetQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankingsGEditBench v2: A Human-Aligned Benchmark for General Image EditingPaintBench: Deterministic Evaluation of Precise Visual Editing (arXiv:2606.00188v1)
83FLUX.1 Kontext [max] Black Forest Labs55±2api $0.080/imagedocs.bfl.ai ↗LMArena leaderboard datasetGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing (arXiv:2509.13399v3)
85Qwen-Image · gguf-q8_0 + Qwen2.5-VL Q8_0 (sd.cpp) Alibaba54±1local~37GBhow to run › LMArena leaderboard datasetT2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)GenExam leaderboard (OpenGVLab/GenExam README, relaxed score)TIIF-Bench: How Does Your T2I Model Follow Your Instructions? (arXiv v3)+8
87LLaDA-Image-Turbo · f16 + LLaDA2 text encoder q8_0 (sd.cpp) Ant Group54±3†local~39GBhow to run › LLaDA-Image: Building Strong Image Generators with Fully Open Training RecipesUltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)
88LongCat-Image · gguf-q4_k_m + Qwen2.5-VL q8_0 (sd.cpp) Meituan53±4local~15GBhow to run › QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)Meituan LongCat — LongCat-Image technical report
90Kling Image 2.1 Kuaishou53±7*api $0.014/imagekling.ai ↗Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
92Wan 2.5 Image-to-Image Preview Alibaba53±4*api $0.030/imagewww.alibabacloud.com ↗LMArena leaderboard dataset
93MiniMax image-01 MiniMax53±5*api $0.0035/imageplatform.minimax.io ↗Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard
94Ideogram 3.0 Ideogram52±2api $0.060/imagefal.ai ↗LMArena leaderboard datasetServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard
97FLUX.2 [klein] 4B · bf16 + Qwen3 4B bf16 (sd.cpp) Black Forest Labs52±2local~20GBhow to run › LMArena leaderboard datasetQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1)GEditBench v2: A Human-Aligned Benchmark for General Image Editing
98P-Image Pruna51±2*api $0.0050/imagereplicate.com ↗LMArena leaderboard datasetRapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings
99Photon Luma AI51±2api $0.019/imagefal.ai ↗LMArena leaderboard datasetMMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard
100Recraft V3 Recraft50±2api $0.040/imagewww.recraft.ai ↗LMArena leaderboard datasetMMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard
101FLUX.1 Kontext [pro] Black Forest Labs50±2api $0.040/imagedocs.bfl.ai ↗LMArena leaderboard datasetMeituan LongCat — LongCat-Image technical reportServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions (arXiv:2603.26174v1)
102GLM-Image Z.ai50±2api $0.015/imagedocs.z.ai ↗LMArena leaderboard datasetQC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)GEditBench v2: A Human-Aligned Benchmark for General Image EditingQwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
104Runway Gen-4 Image Runway50±3*api $0.050/imagedocs.dev.runwayml.com ↗LMArena leaderboard dataset
105Lucid Origin Leonardo.Ai49±3*api $0.017/imagereplicate.com ↗LMArena leaderboard dataset
113Ovis-Image-7B · gguf-q4_0 + Ovis 2.5 (sd.cpp) Alibaba (AIDC-AI)48±7*local~12GBhow to run › Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models (FEPBench)
114FLUX.1 Krea [dev] Black Forest Labs / Krea47±3api $0.025/imagereplicate.com ↗ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World TasksGenExam leaderboard (OpenGVLab/GenExam README, relaxed score)Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation (arXiv:2604.22302v1)
116HiDream-I1-Full HiDream47±2api $0.050/imagefal.ai ↗GenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2)HiDream-ai/HiDream-O1-Image repository README results
118Ideogram 2.0 Ideogram46±2api $0.080/imagereplicate.com ↗LMArena leaderboard datasetMMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2)
120FLUX1.1 [pro] Black Forest Labs46±2api $0.040/imagedocs.bfl.ai ↗LMArena leaderboard datasetMMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboardServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)
126FLUX.1 Kontext [dev] · gguf-q8_0 (sd.cpp) Black Forest Labs44±1local~28GBhow to run › LMArena leaderboard datasetEdit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingMeituan LongCat — LongCat-Image technical reportHP-Edit: A Human-Preference Post-Training Framework for Image Editing (arXiv:2604.19406v1)UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched EditsGEditBench v2: A Human-Aligned Benchmark for General Image Editing+7
127FLUX.1 [dev] · bf16 Black Forest Labs44±1local~29GBhow to run › LMArena leaderboard datasetT2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing)TIIF-Bench: How Does Your T2I Model Follow Your Instructions? (arXiv v3)Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2)+5
131Lumina-Image 2.0 Alpha-VLLM (Shanghai AI Lab)43±4*api $0.075/imagefal.ai ↗TIIF-Bench: How Does Your T2I Model Follow Your Instructions? (arXiv v3)
133BAGEL ByteDance Seed42±1api $0.10/imagefal.ai ↗LMArena leaderboard datasetGenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingTIIF-Bench: How Does Your T2I Model Follow Your Instructions? (arXiv v3)ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks+14
135FLUX.1 [schnell] · bf16 Black Forest Labs42±2local~29GBhow to run › T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboardVerifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)
136OmniGen2 BAAI42±2api $0.15/imagefal.ai ↗Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward ModelingImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World TasksHP-Edit: A Human-Preference Post-Training Framework for Image Editing (arXiv:2604.19406v1)UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched EditsGEditBench v2: A Human-Aligned Benchmark for General Image EditingWEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation (arXiv:2511.11434v1)+6
137Stable Diffusion 3.5 Large · bf16 + T5 fp16 (sd.cpp) Stability AI42±1local~34GBhow to run › LMArena leaderboard datasetGenExam: A Multidisciplinary Text-to-Image Exam (arXiv v5)T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation (arXiv:2505.17613v2)Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (arXiv:2604.24023v2)+4
139Playground v2 (1024px aesthetic) · fp16 (sd.cpp) Playground41±4*local~8.8GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)
141Stable Diffusion 3.5 Medium Stability AI41±3api $0.035/imageplatform.stability.ai ↗T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts (VVRBench), arXiv:2609.35641v1WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)
148Stable Diffusion XL 0.9 (base) · q8_0 (sd.cpp --type) Stability AI40±6*local~4.9GBhow to run › WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)tgxs002/HPSv2 repository README, HPS v2 benchmark table
149Stable Diffusion 3 Medium · fp16 incl. CLIPs + T5 (sd.cpp) Stability AI40±2local~19GBhow to run › T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)HPSv3 repository README, image generation benchmark table (MizzenAI/HPSv3)
153Janus-Pro-7B DeepSeek38±2api $0.0020/imagedeepinfra.com ↗T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (Findings of ACL 2026)DeepSeek-AI — Janus-Pro technical reportMMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2)WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models (XTC-Bench, arXiv:2604.25072v1)
156SDXL-Lightning (4-step UNet) · fp16 (sd.cpp) ByteDance37±3*local~8.8GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)SDXL-Lightning: Progressive Adversarial Diffusion Distillation (arXiv:2402.13929v3)
158Janus-Pro-1B DeepSeek36±4api $0.0005/imagedeepinfra.com ↗DeepSeek-AI — Janus-Pro technical reportWISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)
161SSD-1B · fp16 (sd.cpp) Segmind36±4*local~5.9GBhow to run › EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)
167Stable Diffusion XL 1.0 · fp16 (sd.cpp) Stability AI34±1local~8.8GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World TasksConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty (arXiv v1)+8
170SDXL-Turbo · fp16 (sd.cpp) Stability AI34±2local~8.8GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty (arXiv v1)SDXL-Lightning: Progressive Adversarial Diffusion Distillation (arXiv:2402.13929v3)
178Dreamlike Photoreal 2.0 · q8_0 (sd.cpp --type) Dreamlike.art30±3local~2.1GBhow to run › EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)tgxs002/HPSv2 repository README, HPS v2 benchmark table
183DALL·E Mega (minDALL-E) · fp32 DALL·E Mini / minDALL-E29±4local~8GBhow to run › TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3)HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)tgxs002/HPSv2 repository README, HPS v2 benchmark table
185Openjourney · q8_0 (sd.cpp --type) PromptHero28±2local~2.1GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)ImagenHub: Standardizing the evaluation of conditional image generation models (arXiv v4)HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)tgxs002/HPSv2 repository README, HPS v2 benchmark table
186Stable Diffusion v1.4 · fp32 CompVis27±2local~8GBhow to run › GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty (arXiv v1)ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation (arXiv 2304.05977v4)HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)tgxs002/HPSv2 repository README, HPS v2 benchmark table
187Stable Diffusion v1.3 · fp32 CompVis27±4*local~8GBhow to run › GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1
188Stable Diffusion v1.1 · fp32 CompVis26±3local~8GBhow to run › GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3)REAL: Realism Evaluation of Text-to-Image Generation Models for Effective Data Augmentation (arXiv:2502.10663v1)
189Stable Diffusion v1.2 · fp32 CompVis26±3*local~8GBhow to run › GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)
191Stable Diffusion v1.5 · fp32 Stability AI26±2local~8GBhow to run › GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v1EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3)HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)Evaluating Numerical Reasoning in Text-to-Image Models (GeckoNum, arXiv v3)+1
193LCM Dreamshaper v7 · openvino-fp16 (OpenVINO GenAI) SimianLuo (LCM authors)23±4*local~3GBhow to run › GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3)
—Mage-Flow · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoftnot yet calibratedlocal~14GBhow to run › Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
—Mage-Flow-Base · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoftnot yet calibratedlocal~14GBhow to run › Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
—Mage-Flow-Turbo · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) Microsoftnot yet calibratedlocal~14GBhow to run › Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

+ 88 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