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

Collections

Discover the best community collections!

Collections trending this week

Qwen3.8-27B — Vector Quantized (MLX)

Data-free VQ rungs of Qwen3.8-27B for Apple Silicon. Three rungs, 3.9-4.8 bpw, vision included. Stock mlx-lm. Built with VQLab.

TheDrainFlorist/Qwen3.8-27B-VQ-3.9bpw

Text Generation • 12B • Updated 28 days ago • 344
TheDrainFlorist/Qwen3.8-27B-VQ-4.5bpw

Text Generation • 19B • Updated 28 days ago • 218 • 1
TheDrainFlorist/Qwen3.8-27B-VQ-4.8bpw

Text Generation • 13B • Updated 28 days ago • 226

AStar-Thought-V2

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Paper • 2609.07821 • Published Sep 7 • 7
xxang/AStar-Thought-V2-OpenR1-Math-3k

Viewer • Updated Sep 10 • 2.7k • 87 • 1
xxang/AStar-Thought-V2-Qwen3.5-9B

Text Generation • 9B • Updated Sep 10 • 73 • 2
xxang/AStar-Thought-V2-Qwen3.6-27B

Text Generation • 27B • Updated Sep 10 • 43

AI pathology model

MahmoodLab/CONCH

Image Feature Extraction • Updated May 5, 2024 • 19.8k • 264

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published Aug 24 • 207

meta-llama/Llama-3.2-3B-Instruct

Text Generation • 3B • Updated Oct 24, 2024 • 886k • • 2.97k
meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jun 18, 2025 • 366k • • 5.79k

Qwen3.6 Opus4.7 Heretic Hermes Agent — Editions

Original Qwen3.6 Opus4.7 Heretic Hermes editions. Successor collection linked in the final item.

oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT

Image-Text-to-Text • 35B • Updated Sep 7 • 43 • 1
oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-Llama

Image-Text-to-Text • 0.4B • Updated Sep 7 • 730 • 1
oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-Ollama

Image-Text-to-Text • 0.4B • Updated Sep 7 • 1.25k • 4

Official ExoMind Transformers checkpoints and GGUF releases for scientific reasoning, research, multimodal understanding, and agentic tool use.

AI4SGI/ExoMind

Image-Text-to-Text • 36B • Updated Sep 1 • 26 • 3
AI4SGI/ExoMind-Q4_K_M-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 70
AI4SGI/ExoMind-Q8_0-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 68
AI4SGI/ExoMind-F16-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 33

Minimal Hugging Face port of the CDS-aware mRNABERT RNA language model.

Taykhoom/mRNABERT

Fill-Mask • 0.1B • Updated 17 days ago • 172 • 1

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

Text Generation • 27B • Updated Oct 6 • 5.58k • 89
AEON-7/DFlash-Qwen3.5-27B-Uncensored-NVFP4

Text Generation • 15B • Updated Oct 6 • 159 • 2

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 49

Qwen3.8-27B — Vector Quantized (MLX)

Data-free VQ rungs of Qwen3.8-27B for Apple Silicon. Three rungs, 3.9-4.8 bpw, vision included. Stock mlx-lm. Built with VQLab.

TheDrainFlorist/Qwen3.8-27B-VQ-3.9bpw

Text Generation • 12B • Updated 28 days ago • 344
TheDrainFlorist/Qwen3.8-27B-VQ-4.5bpw

Text Generation • 19B • Updated 28 days ago • 218 • 1
TheDrainFlorist/Qwen3.8-27B-VQ-4.8bpw

Text Generation • 13B • Updated 28 days ago • 226

Qwen3.6 Opus4.7 Heretic Hermes Agent — Editions

Original Qwen3.6 Opus4.7 Heretic Hermes editions. Successor collection linked in the final item.

oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-FT

Image-Text-to-Text • 35B • Updated Sep 7 • 43 • 1
oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-Llama

Image-Text-to-Text • 0.4B • Updated Sep 7 • 730 • 1
oktaydu/Q36-35B-A3B-Opus4.7-Ablit-Heretic-OBLITERATUS-Hermes-MTP-Vision-Ollama

Image-Text-to-Text • 0.4B • Updated Sep 7 • 1.25k • 4

AStar-Thought-V2

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Paper • 2609.07821 • Published Sep 7 • 7
xxang/AStar-Thought-V2-OpenR1-Math-3k

Viewer • Updated Sep 10 • 2.7k • 87 • 1
xxang/AStar-Thought-V2-Qwen3.5-9B

Text Generation • 9B • Updated Sep 10 • 73 • 2
xxang/AStar-Thought-V2-Qwen3.6-27B

Text Generation • 27B • Updated Sep 10 • 43

Official ExoMind Transformers checkpoints and GGUF releases for scientific reasoning, research, multimodal understanding, and agentic tool use.

AI4SGI/ExoMind

Image-Text-to-Text • 36B • Updated Sep 1 • 26 • 3
AI4SGI/ExoMind-Q4_K_M-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 70
AI4SGI/ExoMind-Q8_0-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 68
AI4SGI/ExoMind-F16-GGUF

Image-Text-to-Text • 36B • Updated Sep 1 • 33

AI pathology model

MahmoodLab/CONCH

Image Feature Extraction • Updated May 5, 2024 • 19.8k • 264

Minimal Hugging Face port of the CDS-aware mRNABERT RNA language model.

Taykhoom/mRNABERT

Fill-Mask • 0.1B • Updated 17 days ago • 172 • 1

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published Aug 24 • 207

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

Text Generation • 27B • Updated Oct 6 • 5.58k • 89
AEON-7/DFlash-Qwen3.5-27B-Uncensored-NVFP4

Text Generation • 15B • Updated Oct 6 • 159 • 2

meta-llama/Llama-3.2-3B-Instruct

Text Generation • 3B • Updated Oct 24, 2024 • 886k • • 2.97k
meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jun 18, 2025 • 366k • • 5.79k

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 49

Previous
1
...
2,089
2,090
2,091
2,092
2,093
...
24,681
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs