Gemma4
🔥
33
Chat with Gemma 4 models fully in the browser via MediaPipe
gemma4
-
-
litert-community/gemma-4-31B-it-litert-lm
Updated • 489 • 2 -
google/gemma-4-12B-it
Any-to-Any • 12B • Updated • 3.31M • 1.49k -
google/gemma-4-26B-A4B
Image-Text-to-Text • 27B • Updated • 139k • 383 -
google/gemma-4-31B
Image-Text-to-Text • 33B • Updated • 705k • 512 -
google/gemma-4-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 8.36M • • 1.44k -
google/gemma-4-E2B-it
Any-to-Any • 5B • Updated • 3.42M • 919 -
google/gemma-4-E2B
Any-to-Any • 5B • Updated • 80.6k • 446 -
google/gemma-4-E4B
Any-to-Any • 8B • Updated • 405k • 400 -
google/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 5.01M • 1.5k -
google/gemma-4-31B-it
Image-Text-to-Text • 31B • Updated • 8.46M • • 3.64k -
google/gemma-4-12B
Any-to-Any • 12B • Updated • 99.9k • 713 -
LilaRest/gemma-4-31B-it-NVFP4-turbo
Text Generation • 33B • Updated • 294k • 302 -
RedHatAI/gemma-4-31B-it-NVFP4
Image-Text-to-Text • 33B • Updated • 84.9k • 57 -
HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP
Image-Text-to-Text • 31B • Updated • 367k • 142 -
RedHatAI/gemma-4-31B-it-FP8-block
Image-Text-to-Text • 31B • Updated • 1.2M • 45 -
nvidia/Gemma-4-31B-IT-NVFP4
Text Generation • 21B • Updated • 2.14M • • 560 -
unsloth/gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 490k • 593 -
bartowski/google_gemma-4-31B-it-GGUF
Image-Text-to-Text • 31B • Updated • 53.7k • 87 -
RockToken/gemma4_31b_to_e4b_onpolicy_math_2k
Text Generation • 9B • Updated • 10 -
Darkhn-Quants-4/Gemma-4-31B-Animus-V15.1-Swa-W8A16-PTQ
33B • Updated • 8 -
nvidia/diffusiongemma-26B-A4B-it-NVFP4
Text Generation • 14B • Updated • 572k • 124 -
google/diffusiongemma-26B-A4B-it
Image-Text-to-Text • 26B • Updated • 1.58M • 1.19k -
hyperspaceai/diffusiongemma-26B-A4B-asym-2bitexp-GGUF
Text Generation • 25B • Updated • 77 • 4 -
unsloth/diffusiongemma-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 20.5k • 387 -
RedHatAI/diffusiongemma-26B-A4B-it-NVFP4
Image-Text-to-Text • 26B • Updated • 9.15k • 19 -
google/siglip2-so400m-patch16-naflex
Zero-Shot Image Classification • 1B • Updated • 377k • 82 -
google/tabfm-1.0.0-jax
Tabular Classification • Updated • 3.54k • 9 -
nvidia/LocateAnything-3B
Image-Text-to-Text • 4B • Updated • 94.2k • 2.96k -
srv-sngh/LocateAnything-3B-mlx-nvfp4
Image-Text-to-Text • 1B • Updated • 35 -
Reza2kn/LocateAnything-3B-ONNX-WebGPU-INT4
Object Detection • Updated • 26 • 12 -
nvidia/Nemotron-3-Embed-8B-BF16
Sentence Similarity • 8B • Updated • 89.3k • 91 -
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 922k • • 1.07k -
BotgenossenGmbH/nemotron-3.5-asr-de-telephony
Automatic Speech Recognition • Updated • 15 • 5 -
nvidia/llama-embed-nemotron-8b
Feature Extraction • 8B • Updated • 466k • 170 -
enzoescipy/llama-embed-nemotron-8b-model2vec-pca3
512k • Updated • 7 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 2.43M • • 1.86k -
poisson-fish/Llama-3.1-Nemotron-70B-Instruct-GGUF
71B • Updated • 118 • 1 -
microsoft/Fara1.5-27B
Image-Text-to-Text • 27B • Updated • 2.74k • • 287 -
Qwen/Qwen3.6-35B-A3B
Image-Text-to-Text • 36B • Updated • 5.23M • • 2.74k -
nvidia/Qwen3.6-35B-A3B-NVFP4
Text Generation • 19B • Updated • 11.7M • 573 -
neko-legends/Qwen3.6-35B-A3B-NVFP4-MTP-GGUF
Text Generation • 36B • Updated • 5.54k • 4 -
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
Image-Text-to-Text • 27B • Updated • 2.63M • 2.25k -
microsoft/VibeVoice-Realtime-0.5B
Text-to-Speech • 1B • Updated • 605k • 1.28k -
microsoft/phi-4
Text Generation • 15B • Updated • 654k • • 2.29k -
ankk98/dspark-gemma4-12b-block7-Q4_0-GGUF
3B • Updated • 320 • 4 -
deepseek-ai/dspark_gemma4_12b_block7
3B • Updated • 1.64k • 44 -
deepseek-ai/DeepSeek-V4-Flash
Text Generation • 291B • Updated • 1.74M • • 2.15k -
heihei/llm-psychology-raw-data
Updated • 33 -
deepseek-ai/dspark_qwen3_4b_block7
1B • Updated • 7.23k • 43 -
litert-community/gemma-4-12B-it-litert-lm
Updated • 11.7k • 51 -
Snowflake/AgentWorldModel-1K
Updated • 927 • 71 -
deepset/tinyroberta-squad2
Question Answering • 81.5M • Updated • 194k • • 114 -
LiheYoung/depth-anything-small-hf
Depth Estimation • 24.8M • Updated • 57.7k • 36 -
distilbert/distilbert-base-uncased-finetuned-sst-2-english
Text Classification • 67M • Updated • 3.62M • • 943 -
lordtt13/emo-mobilebert
Text Classification • 21.2M • Updated • 1.02k • • 5
