Skip to main content
NeuroBrixNeuroBrix
Back to Hub

Compare Models

Side-by-side comparison of AI models available on the NeuroBrix Hub.

AllLLMCODEVLMMULTIMODALTTSSTTAUDIO_LLMIMAGEUPSCALERVIDEO
ModelOrganizationCategorySizeDownloadsTags
chatterboxResembleAITTS2.0 GiB156
Text-to-SpeechVoice CloningNatural Prosody+2
whisper-largeopenaiSTT5.8 GiB70
Speech-to-TextASRMultilingual+3
TinyLlama-1.1B-Chat-v1.0TinyLlamaLLM2.1 GiB70
llmchat
whisper-large-v3-turboopenaiSTT1.5 GiB53
Speech-to-TextASRMultilingual+3
Wan2.1-T2V-1.3B-DiffusersWan-AIVIDEO26.9 GiB51
diffusiontext-to-video
Sana_1600M_1024px_MultiLing_diffusersEfficient-Large-ModelIMAGE9.0 GiB49
Text-to-ImageDiffusionMultilingual+3
PixArt-Sigma-XL-2-1024-MSPixArt-alphaIMAGE20.3 GiB42
Text-to-ImageDiffusion Transformer1024px+2
CogVideoX-2bzai-orgVIDEO12.9 GiB41
diffusiontext-to-video
Wan2.2-I2V-A14B-DiffusersWan-AIVIDEO118.0 GiB39
diffusionimage-to-video
DeepSeek-Coder-V2-Lite-Instructdeepseek-aiCODE29.9 GiB38
codemoemla+2
PixArt-XL-2-1024-MSPixArt-alphaIMAGE20.3 GiB35
Text-to-ImageDiffusion Transformer1024px+2
Qwen3-VL-30B-A3B-ThinkingQwenMULTIMODAL57.9 GiB33
vlmmultimodalmoe+4
Qwen3-30B-A3B-Thinking-2507QwenLLM56.9 GiB31
LLMReasoningMixture-of-Experts+3
Wan2.1-I2V-14B-480P-DiffusersWan-AIVIDEO84.4 GiB30
diffusionimage-to-video
SwinIR-001_classicalSR_DIV2K_s48w8_SwinIR-M_x4JingyunLiangUPSCALER43.2 MiB30
Super-Resolution4x UpscalingSwin Transformer+2
Kokoro-82MhexgradTTS352.9 MiB29
Text-to-SpeechLightweight82M+2
Qwen3-Coder-30B-A3B-InstructQwenCODE56.9 GiB28
CodeCodingMixture-of-Experts+4
GLM-4.1V-9B-Thinkingzai-orgVLM19.2 GiB28
vlmvisionreasoning+2
swin2SR-classical-sr-x2-64caidasUPSCALER47.1 MiB27
Super-Resolution2x UpscalingSwin Transformer V2+2
Open-Sora-v2hpcai-techVIDEO42.4 GiB27
diffusiontext-to-video
granite-speech-3.3-8bibm-graniteAUDIO_LLM16.1 GiB27
Audio-LLMSpeech RecognitionSpeech Translation+3
Real-ESRGAN-RealESRGAN_x4plusxinntaoUPSCALER63.9 MiB26
Super-Resolution4x UpscalingPhoto Restoration+3
HAT-HAT-L_SRx4_ImageNet-pretrainXPixelGroupUPSCALER145.8 MiB25
Super-Resolution4x UpscalingHybrid Attention Transformer+1
Allegrorhymes-aiVIDEO23.6 GiB25
diffusiontext-to-video
Janus-Pro-7Bdeepseek-aiMULTIMODAL13.8 GiB25
Allegro-TI2Vrhymes-aiVIDEO24.3 GiB24
diffusionimage-to-video
swin2SR-classical-sr-x4-64caidasUPSCALER47.6 MiB24
Super-Resolution4x UpscalingSwin Transformer V2+2
Flex.1-alphaostrisIMAGE24.5 GiB23
Text-to-ImageRectified FlowFine-tunable+3
mochi-1-previewgenmoVIDEO38.2 GiB23
diffusiontext-to-video
Qwen3-Omni-30B-A3B-InstructQwenMULTIMODAL65.8 GiB23
omnimultimodalmoe+5
s1-minifishaudioTTS2.6 GiB22
Text-to-SpeechVoice CloningMultilingual+2
parakeet-tdt-1.1bnvidiaSTT4.0 GiB21
Speech-to-TextASREnglish+3
MiniCPM-o-4_5openbmbMULTIMODAL19.3 GiB21
omnimultimodalvision+5
Wan2.1-VACE-1.3B-diffusersWan-AIVIDEO18.2 GiB21
diffusionvideo-editingtext-to-video
SwinIR-001_classicalSR_DF2K_s64w8_SwinIR-M_x2JingyunLiangUPSCALER42.7 MiB21
Super-Resolution2x UpscalingSwin Transformer+2
swin2SR-realworld-sr-x4-64-bsrgan-psnrcaidasUPSCALER46.9 MiB21
Super-Resolution4x UpscalingSwin Transformer V2+3
canary-qwen-2.5bnvidiaAUDIO_LLM4.7 GiB21
Audio-LLMSpeech RecognitionEnglish+3
deepseek-moe-16b-chatdeepseek-aiLLM30.5 GiB20
llmmoechat
Voxtral-Mini-3B-2507mistralaiAUDIO_LLM8.7 GiB20
Audio-LLMSpeech RecognitionAudio Understanding+3
orpheus-3b-0.1-ftcanopylabsTTS14.1 GiB19
Text-to-SpeechLLM-basedLlama 3+3
CogVideoX-5b-I2Vzai-orgVIDEO21.0 GiB18
diffusionimage-to-video
VibeVoice-1.5BmicrosoftTTS5.0 GiB17
Text-to-SpeechMulti-SpeakerLong-Form+3
granite-3.1-1b-a400m-instructibm-graniteLLM2.6 GiB17
llmmoegranite+1
Ming-Lite-Omni-1.5inclusionAIMULTIMODAL51.1 GiB16
HAT-HAT-S_SRx4XPixelGroupUPSCALER34.8 MiB15
Super-Resolution4x UpscalingHybrid Attention Transformer+1
Real-ESRGAN-RealESRGAN_x2ai-foreverUPSCALER63.9 MiB14
Super-Resolution2x UpscalingGAN+1
SANA-Video_2B_720p_diffusersEfficient-Large-ModelVIDEO17.1 GiB13
diffusiontext-to-video
Real-ESRGAN-RealESRGAN_x8ai-foreverUPSCALER64.0 MiB11
Super-Resolution8x UpscalingGAN+1
Sana_1600M_4Kpx_BF16_diffusersEfficient-Large-ModelIMAGE12.0 GiB4
Text-to-ImageDiffusion4K Resolution+3

By Category

LLM4 models
TinyLlama/TinyLlama-1.1B-Chat-v1.0 (2.1 GiB)Qwen/Qwen3-30B-A3B-Thinking-2507 (56.9 GiB)deepseek-ai/deepseek-moe-16b-chat (30.5 GiB)ibm-granite/granite-3.1-1b-a400m-instruct (2.6 GiB)
Total: 92.0 GiB
CODE2 models
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct (29.9 GiB)Qwen/Qwen3-Coder-30B-A3B-Instruct (56.9 GiB)
Total: 86.8 GiB
VLM1 model
zai-org/GLM-4.1V-9B-Thinking (19.2 GiB)
Total: 19.2 GiB
MULTIMODAL5 models
Qwen/Qwen3-VL-30B-A3B-Thinking (57.9 GiB)deepseek-ai/Janus-Pro-7B (13.8 GiB)Qwen/Qwen3-Omni-30B-A3B-Instruct (65.8 GiB)openbmb/MiniCPM-o-4_5 (19.3 GiB)inclusionAI/Ming-Lite-Omni-1.5 (51.1 GiB)
Total: 207.8 GiB
TTS5 models
ResembleAI/chatterbox (2.0 GiB)hexgrad/Kokoro-82M (352.9 MiB)fishaudio/s1-mini (2.6 GiB)canopylabs/orpheus-3b-0.1-ft (14.1 GiB)microsoft/VibeVoice-1.5B (5.0 GiB)
Total: 24.2 GiB
STT3 models
openai/whisper-large (5.8 GiB)openai/whisper-large-v3-turbo (1.5 GiB)nvidia/parakeet-tdt-1.1b (4.0 GiB)
Total: 11.3 GiB
AUDIO_LLM3 models
ibm-granite/granite-speech-3.3-8b (16.1 GiB)nvidia/canary-qwen-2.5b (4.7 GiB)mistralai/Voxtral-Mini-3B-2507 (8.7 GiB)
Total: 29.6 GiB
IMAGE5 models
Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers (9.0 GiB)PixArt-alpha/PixArt-Sigma-XL-2-1024-MS (20.3 GiB)PixArt-alpha/PixArt-XL-2-1024-MS (20.3 GiB)ostris/Flex.1-alpha (24.5 GiB)Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers (12.0 GiB)
Total: 86.2 GiB
UPSCALER10 models
JingyunLiang/SwinIR-001_classicalSR_DIV2K_s48w8_SwinIR-M_x4 (43.2 MiB)caidas/swin2SR-classical-sr-x2-64 (47.1 MiB)xinntao/Real-ESRGAN-RealESRGAN_x4plus (63.9 MiB)XPixelGroup/HAT-HAT-L_SRx4_ImageNet-pretrain (145.8 MiB)caidas/swin2SR-classical-sr-x4-64 (47.6 MiB)JingyunLiang/SwinIR-001_classicalSR_DF2K_s64w8_SwinIR-M_x2 (42.7 MiB)caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr (46.9 MiB)XPixelGroup/HAT-HAT-S_SRx4 (34.8 MiB)ai-forever/Real-ESRGAN-RealESRGAN_x2 (63.9 MiB)ai-forever/Real-ESRGAN-RealESRGAN_x8 (64.0 MiB)
Total: 600.0 MiB
VIDEO11 models
Wan-AI/Wan2.1-T2V-1.3B-Diffusers (26.9 GiB)zai-org/CogVideoX-2b (12.9 GiB)Wan-AI/Wan2.2-I2V-A14B-Diffusers (118.0 GiB)Wan-AI/Wan2.1-I2V-14B-480P-Diffusers (84.4 GiB)hpcai-tech/Open-Sora-v2 (42.4 GiB)rhymes-ai/Allegro (23.6 GiB)rhymes-ai/Allegro-TI2V (24.3 GiB)genmo/mochi-1-preview (38.2 GiB)Wan-AI/Wan2.1-VACE-1.3B-diffusers (18.2 GiB)zai-org/CogVideoX-5b-I2V (21.0 GiB)Efficient-Large-Model/SANA-Video_2B_720p_diffusers (17.1 GiB)
Total: 427.0 GiB