Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes.

DavidAU/Qwen3.5-40B-RoughHouse-Quantum-Madness-Star-Trek-TNG-DS9-PKD-Deckard-Uncensored-Heretic-Thinking

Image-Text-to-Text • 40B • Updated 25 days ago • 95 • 1
DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

Image-Text-to-Text • 40B • Updated 5 days ago • 11k • 152
DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking

Image-Text-to-Text • 40B • Updated 29 days ago • 769 • 42
DavidAU/Qwen3.5-40B-RoughHouse-Claude-4.6-Opus-Polar-Deckard-Uncensored-Heretic-Thinking

Image-Text-to-Text • 40B • Updated 29 days ago • 701 • 16

VBVR: A Very Big Video Reasoning Suite

Video-Reason/VBVR-Wan2.2

Image-to-Video • Updated 1 day ago • 223 • 127
Video-Reason/VBVR-Dataset

Viewer • Updated 15 days ago • 1M • 1.65k • 50
Video-Reason/VBVR-Bench-Data

Viewer • Updated 15 days ago • 500 • 998 • 9
Video-Reason/video-mcp

Viewer • Updated 15 days ago • 3.91k • 175 • 1

A 0.6-billion-parameter Hindi language models trained entirely from scratch.

Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi

Paper • 2603.03508 • Published Mar 3 • 3
Polygl0t/LilMoo-v0.1

Text Generation • 0.7B • Updated Mar 5 • 13
Polygl0t/LilMoo-v0.2

Text Generation • 0.7B • Updated Mar 5 • 12
Polygl0t/gigalekh-v1

Viewer • Updated Mar 5 • 83.6M • 198

Qwen3.5-35B-A3B Heretic MLX

TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-mxfp8

Image-Text-to-Text • 35B • Updated Mar 3 • 1.2k • 4
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-mxfp4

Image-Text-to-Text • 35B • Updated Mar 3 • 366 • 1
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit

Image-Text-to-Text • 35B • Updated Mar 3 • 1.27k • 4
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-6bit

Image-Text-to-Text • 35B • Updated Mar 3 • 562 • 3

A 0.6B Bengali Language Model that Outperforms Qwen.

Polygl0t/LilTii-v0.1

Text Generation • 0.7B • Updated Mar 5 • 14
Polygl0t/LilTii-v0.2

Text Generation • 0.7B • Updated Mar 5 • 24
Polygl0t/gigakriya-v1

Viewer • Updated Mar 5 • 41.6M • 80
Polygl0t/bengali-edu-qwen-annotations

Viewer • Updated Mar 5 • 320k • 30

about 5 hours ago

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization

Paper • 2505.16467 • Published May 22, 2025
IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data

Paper • 2506.02449 • Published Jun 3, 2025 • 1
Localizing Persona Representations in LLMs

Paper • 2505.24539 • Published May 30, 2025
Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Paper • 2507.21509 • Published Jul 29, 2025 • 33

RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-lm-mxfp4

Text Generation • 35B • Updated Feb 24 • 1.84k • 5
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-vlm-mxfp4

Text Generation • 7B • Updated Feb 24 • 582 • 2
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-vlm-nvfp4

Text Generation • 9B • Updated Feb 24 • 290
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-lm-nvfp4

Text Generation • 35B • Updated Feb 24 • 259

Efficient Drop-In Replacement for the Classification Head in Language Model Inference. https://github.com/embedl/flash-head

about 5 hours ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead

Image-Text-to-Text • 2B • Updated 1 day ago • 926 • 7
embedl/Qwen3-1.7B-FlashHead-W4A16

2B • Updated 1 day ago • 140 • 3
embedl/gemma-3-270m-it-FlashHead

0.3B • Updated 1 day ago • 211 • 3
embedl/Qwen3-0.6B-FlashHead

0.6B • Updated 1 day ago • 85 • 4

awq quantization

QuantTrio/Qwen3.5-35B-A3B-AWQ

Image-Text-to-Text • 36B • Updated Feb 26 • 154k • 17
QuantTrio/Qwen3.5-122B-A10B-AWQ

Image-Text-to-Text • 125B • Updated Feb 26 • 57.2k • 25
QuantTrio/Qwen3.5-397B-A17B-AWQ

Image-Text-to-Text • Updated Mar 2 • 21.8k • 9
QuantTrio/Qwen3.5-27B-AWQ

Image-Text-to-Text • 28B • Updated Mar 2 • 367k • 41

Qwen3.5 Heretic

coder3101/Qwen3.5-122B-A10B-heretic

Image-Text-to-Text • 122B • Updated Mar 8 • 240 • 10
coder3101/Qwen3.5-35B-A3B-heretic

Image-Text-to-Text • 35B • Updated Mar 3 • 120 • 5
coder3101/Qwen3.5-27B-heretic

Image-Text-to-Text • 27B • Updated Feb 25 • 5.4k • 63
coder3101/Qwen3.5-9B-heretic

Image-Text-to-Text • 9B • Updated Mar 4 • 199 • 2

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes.

DavidAU/Qwen3.5-40B-RoughHouse-Quantum-Madness-Star-Trek-TNG-DS9-PKD-Deckard-Uncensored-Heretic-Thinking

Image-Text-to-Text • 40B • Updated 25 days ago • 95 • 1
DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

Image-Text-to-Text • 40B • Updated 5 days ago • 11k • 152
DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking

Image-Text-to-Text • 40B • Updated 29 days ago • 769 • 42
DavidAU/Qwen3.5-40B-RoughHouse-Claude-4.6-Opus-Polar-Deckard-Uncensored-Heretic-Thinking

Image-Text-to-Text • 40B • Updated 29 days ago • 701 • 16

about 5 hours ago

Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization

Paper • 2505.16467 • Published May 22, 2025
IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data

Paper • 2506.02449 • Published Jun 3, 2025 • 1
Localizing Persona Representations in LLMs

Paper • 2505.24539 • Published May 30, 2025
Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Paper • 2507.21509 • Published Jul 29, 2025 • 33

VBVR: A Very Big Video Reasoning Suite

Video-Reason/VBVR-Wan2.2

Image-to-Video • Updated 1 day ago • 223 • 127
Video-Reason/VBVR-Dataset

Viewer • Updated 15 days ago • 1M • 1.65k • 50
Video-Reason/VBVR-Bench-Data

Viewer • Updated 15 days ago • 500 • 998 • 9
Video-Reason/video-mcp

Viewer • Updated 15 days ago • 3.91k • 175 • 1

RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-lm-mxfp4

Text Generation • 35B • Updated Feb 24 • 1.84k • 5
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-vlm-mxfp4

Text Generation • 7B • Updated Feb 24 • 582 • 2
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-vlm-nvfp4

Text Generation • 9B • Updated Feb 24 • 290
RepublicOfKorokke/Qwen3.5-35B-A3B-mlx-lm-nvfp4

Text Generation • 35B • Updated Feb 24 • 259

A 0.6-billion-parameter Hindi language models trained entirely from scratch.

Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi

Paper • 2603.03508 • Published Mar 3 • 3
Polygl0t/LilMoo-v0.1

Text Generation • 0.7B • Updated Mar 5 • 13
Polygl0t/LilMoo-v0.2

Text Generation • 0.7B • Updated Mar 5 • 12
Polygl0t/gigalekh-v1

Viewer • Updated Mar 5 • 83.6M • 198

Efficient Drop-In Replacement for the Classification Head in Language Model Inference. https://github.com/embedl/flash-head

about 5 hours ago

embedl/Cosmos-Reason2-2B-W4A16-Edge2-FlashHead

Image-Text-to-Text • 2B • Updated 1 day ago • 926 • 7
embedl/Qwen3-1.7B-FlashHead-W4A16

2B • Updated 1 day ago • 140 • 3
embedl/gemma-3-270m-it-FlashHead

0.3B • Updated 1 day ago • 211 • 3
embedl/Qwen3-0.6B-FlashHead

0.6B • Updated 1 day ago • 85 • 4

Qwen3.5-35B-A3B Heretic MLX

TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-mxfp8

Image-Text-to-Text • 35B • Updated Mar 3 • 1.2k • 4
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-mxfp4

Image-Text-to-Text • 35B • Updated Mar 3 • 366 • 1
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-4bit

Image-Text-to-Text • 35B • Updated Mar 3 • 1.27k • 4
TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-6bit

Image-Text-to-Text • 35B • Updated Mar 3 • 562 • 3

awq quantization

QuantTrio/Qwen3.5-35B-A3B-AWQ

Image-Text-to-Text • 36B • Updated Feb 26 • 154k • 17
QuantTrio/Qwen3.5-122B-A10B-AWQ

Image-Text-to-Text • 125B • Updated Feb 26 • 57.2k • 25
QuantTrio/Qwen3.5-397B-A17B-AWQ

Image-Text-to-Text • Updated Mar 2 • 21.8k • 9
QuantTrio/Qwen3.5-27B-AWQ

Image-Text-to-Text • 28B • Updated Mar 2 • 367k • 41

A 0.6B Bengali Language Model that Outperforms Qwen.

Polygl0t/LilTii-v0.1

Text Generation • 0.7B • Updated Mar 5 • 14
Polygl0t/LilTii-v0.2

Text Generation • 0.7B • Updated Mar 5 • 24
Polygl0t/gigakriya-v1

Viewer • Updated Mar 5 • 41.6M • 80
Polygl0t/bengali-edu-qwen-annotations

Viewer • Updated Mar 5 • 320k • 30

Qwen3.5 Heretic

coder3101/Qwen3.5-122B-A10B-heretic

Image-Text-to-Text • 122B • Updated Mar 8 • 240 • 10
coder3101/Qwen3.5-35B-A3B-heretic

Image-Text-to-Text • 35B • Updated Mar 3 • 120 • 5
coder3101/Qwen3.5-27B-heretic

Image-Text-to-Text • 27B • Updated Feb 25 • 5.4k • 63
coder3101/Qwen3.5-9B-heretic

Image-Text-to-Text • 9B • Updated Mar 4 • 199 • 2

Previous
1
...
31
32
33
34
35
...
19,771
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs