Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 18 • 536k • • 1.24k
BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 36.3M • • 3.42k
prism-ml/Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 17 • 860k • 798

To-test-embeddings

BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 36.3M • • 3.42k

empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Image-Text-to-Text • 9B • Updated Jul 14 • 439k • 2.63k
mradermacher/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF

12B • Updated Jun 9 • 385 • 5
mradermacher/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-i1-GGUF

9B • Updated Apr 25 • 646 • 4
lmstudio-community/gemma-4-E4B-it-GGUF

8B • Updated Jul 20 • 628k • 64

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.06M • • 5.47k

FADE TOFU Checkpoints

Checkpoints for reproducing FADE on TOFU (arXiv:2510.12981): full model, retain-only oracles, and unlearned LoRA checkpoints.

sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-ga

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-gd

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-npo

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-dpo

Updated Jul 23

Icon Search Experiments

https://lucide-similarity-explorer.vercel.app/

Cortiq-Labs/IconClip-ViT-L-14-text-encoder-ONNX

Feature Extraction • Updated May 20 • 16 • 2
Cortiq-Labs/iconclip-search-benchmark

Viewer • Updated May 20 • 22.9k • 128 • 1
Running

IconClip Search Demo

🔍

Free-text → 22k icons via IconClip q8 ONNX, 100% in-browser.

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 2.3M • 1.9k

Directly loadable Apple silicon MLX-LM conversions of Antares-350M and Antares-1B in BF16, 8-bit, 6-bit, 4-bit, and 3-bit formats.

imadreamerboy/antares-350m-bf16-mlx

Text Generation • 0.4B • Updated Jul 23
imadreamerboy/antares-350m-8bit-mlx

Text Generation • 99.1M • Updated Jul 23
imadreamerboy/antares-350m-6bit-mlx

Text Generation • 77.1M • Updated Jul 23
imadreamerboy/antares-350m-4bit-mlx

Text Generation • 55.1M • Updated Jul 23

Qwen/Qwen3-VL-30B-A3B-Instruct

Image-Text-to-Text • 31B • Updated Nov 26, 2025 • 378k • • 593
mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit

Image-Text-to-Text • Updated Oct 11, 2025 • 1.24k • 9

FADE TOFU Checkpoints

Checkpoints for reproducing FADE on TOFU (arXiv:2510.12981): full model, retain-only oracles, and unlearned LoRA checkpoints.

sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-ga

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-gd

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-npo

Updated Jul 23
sungjuncho/Llama-3.1-8B-fade-tofu-unlearned-dpo

Updated Jul 23

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 18 • 536k • • 1.24k
BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 36.3M • • 3.42k
prism-ml/Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 17 • 860k • 798

Icon Search Experiments

https://lucide-similarity-explorer.vercel.app/

Cortiq-Labs/IconClip-ViT-L-14-text-encoder-ONNX

Feature Extraction • Updated May 20 • 16 • 2
Cortiq-Labs/iconclip-search-benchmark

Viewer • Updated May 20 • 22.9k • 128 • 1
Running

IconClip Search Demo

🔍

Free-text → 22k icons via IconClip q8 ONNX, 100% in-browser.

To-test-embeddings

BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 36.3M • • 3.42k

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • 2B • Updated Jan 29 • 2.3M • 1.9k

empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

Image-Text-to-Text • 9B • Updated Jul 14 • 439k • 2.63k
mradermacher/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-GGUF

12B • Updated Jun 9 • 385 • 5
mradermacher/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-i1-GGUF

9B • Updated Apr 25 • 646 • 4
lmstudio-community/gemma-4-E4B-it-GGUF

8B • Updated Jul 20 • 628k • 64

Directly loadable Apple silicon MLX-LM conversions of Antares-350M and Antares-1B in BF16, 8-bit, 6-bit, 4-bit, and 3-bit formats.

imadreamerboy/antares-350m-bf16-mlx

Text Generation • 0.4B • Updated Jul 23
imadreamerboy/antares-350m-8bit-mlx

Text Generation • 99.1M • Updated Jul 23
imadreamerboy/antares-350m-6bit-mlx

Text Generation • 77.1M • Updated Jul 23
imadreamerboy/antares-350m-4bit-mlx

Text Generation • 55.1M • Updated Jul 23

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.06M • • 5.47k

Qwen/Qwen3-VL-30B-A3B-Instruct

Image-Text-to-Text • 31B • Updated Nov 26, 2025 • 378k • • 593
mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit

Image-Text-to-Text • Updated Oct 11, 2025 • 1.24k • 9

Previous
1
...
811
812
813
814
815
...
22,705
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs