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

Paza is a collection of speech models & benchmarks for low resource languages by the Microsoft Research Africa - Nairobi Lab

Running

Agents

20

PazaBench

🥇

20

ASR Leaderboard for low resource languages
microsoft/paza-Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Feb 4 • 157 • 4
microsoft/paza-whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated Feb 4 • 458 • 8

about 16 hours ago

datalab-to/chandra

Image-Text-to-Text • 9B • Updated Mar 26 • 207k • 525
datalab-to/chandra-ocr-2

Image-Text-to-Text • 5B • Updated Mar 18 • 2M • 391
datalab-to/lift

Image-Text-to-Text • 10B • Updated about 21 hours ago • 66
datalab-to/surya-ocr-2

Image-Text-to-Text • 0.7B • Updated 24 days ago • 304k • 47

From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents

mlfoundations/Gelato-30B-A3B

Image-Text-to-Text • 31B • Updated Nov 15, 2025 • 74 • 33
mlfoundations/Click-100k

Viewer • Updated Nov 11, 2025 • 101k • 841 • 18
🍨 Gelato-30B-A3B Checkpoints

Collection

Intermediate checkpoints for Gelato-30B-A3B. Refer to https://github.com/mlfoundations/gelato for more details. • 29 items • Updated Oct 29, 2025 • 1
mlfoundations/gelato-osworld-agent-trajectories

Viewer • Updated Nov 6, 2025 • 13.5k • 321 • 2

High quality quants for Mac Studio (MLX)

Aiming to create the best quality quants for a single Mac Studio

mlx-community/GLM-5.2-DQ4plus-q8

Text Generation • 743B • Updated 3 days ago • 2.47k • 7
mlx-community/Kimi-K2.7-Code-mlx-DQ3_K_M-q8

Text Generation • 1T • Updated 4 days ago • 880 • 3
mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8

Text Generation • 1T • Updated Apr 21 • 100k • 8
mlx-community/GLM-5.1-DQ4plus-q8

Text Generation • 744B • Updated Apr 12 • 2.08k • 6

Qwen3-VL-abliterated

huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

Image-Text-to-Text • 31B • Updated Dec 15, 2025 • 3.29k • 87
huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated Dec 15, 2025 • 9.09k • 68
huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated

Image-Text-to-Text • 9B • Updated Dec 15, 2025 • 17.1k • 185
huihui-ai/Huihui-Qwen3-VL-4B-Thinking-abliterated

Image-Text-to-Text • 4B • Updated Dec 15, 2025 • 103 • 28

This is the official set of weights for the paper “Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions.”

lchen1019/LlavaQwen2-Align-TI-1B

Image-Text-to-Text • 1B • Updated Feb 11 • 5
lchen1019/LlavaQwen3-Align-TI-2B

2B • Updated Oct 29, 2025 • 3
lchen1019/LlavaQwen2-Align-TI-2B

2B • Updated Oct 29, 2025 • 4
lchen1019/LlavaQwen3-Align-TI-1B

1B • Updated Oct 29, 2025 • 4

Checkpoints, data and logs of MemoryVLA & MemoryVLA+. https://github.com/shihao1895/MemoryVLA

shihao1895/memvla-libero-spatial

Updated Nov 5, 2025 • 66
shihao1895/memvla-libero-object

Updated Nov 5, 2025 • 29
shihao1895/memvla-libero-goal

Updated Nov 5, 2025 • 34
shihao1895/memvla-libero-100

Updated Nov 5, 2025 • 180

Pretrained ARC-Encoders and a fine-tuning dataset: context compression for unmodified LLMs.

ARC-Encoder: learning compressed text representations for large language models

Paper • 2510.20535 • Published Oct 23, 2025 • 10
kyutai/ARC8_Encoder_Llama

Feature Extraction • Updated Nov 5, 2025 • 12 • 3
kyutai/ARC_finetuning

Preview • Updated Oct 24, 2025 • 59 • 1
kyutai/ARC8_Encoder_multi

Feature Extraction • Updated Nov 5, 2025 • 54 • 7

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 276
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

Paper • 2510.08002 • Published Oct 9, 2025 • 24
Self-Improving LLM Agents at Test-Time

Paper • 2510.07841 • Published Oct 9, 2025 • 10
The Denario project: Deep knowledge AI agents for scientific discovery

Paper • 2510.26887 • Published Oct 30, 2025 • 8

t-tech/flex-sae

Updated Oct 27, 2025 • 1 • 12

Paza is a collection of speech models & benchmarks for low resource languages by the Microsoft Research Africa - Nairobi Lab

Running

Agents

20

PazaBench

🥇

20

ASR Leaderboard for low resource languages
microsoft/paza-Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Feb 4 • 157 • 4
microsoft/paza-whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated Feb 4 • 458 • 8

This is the official set of weights for the paper “Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions.”

lchen1019/LlavaQwen2-Align-TI-1B

Image-Text-to-Text • 1B • Updated Feb 11 • 5
lchen1019/LlavaQwen3-Align-TI-2B

2B • Updated Oct 29, 2025 • 3
lchen1019/LlavaQwen2-Align-TI-2B

2B • Updated Oct 29, 2025 • 4
lchen1019/LlavaQwen3-Align-TI-1B

1B • Updated Oct 29, 2025 • 4

about 16 hours ago

datalab-to/chandra

Image-Text-to-Text • 9B • Updated Mar 26 • 207k • 525
datalab-to/chandra-ocr-2

Image-Text-to-Text • 5B • Updated Mar 18 • 2M • 391
datalab-to/lift

Image-Text-to-Text • 10B • Updated about 21 hours ago • 66
datalab-to/surya-ocr-2

Image-Text-to-Text • 0.7B • Updated 24 days ago • 304k • 47

Checkpoints, data and logs of MemoryVLA & MemoryVLA+. https://github.com/shihao1895/MemoryVLA

shihao1895/memvla-libero-spatial

Updated Nov 5, 2025 • 66
shihao1895/memvla-libero-object

Updated Nov 5, 2025 • 29
shihao1895/memvla-libero-goal

Updated Nov 5, 2025 • 34
shihao1895/memvla-libero-100

Updated Nov 5, 2025 • 180

From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents

mlfoundations/Gelato-30B-A3B

Image-Text-to-Text • 31B • Updated Nov 15, 2025 • 74 • 33
mlfoundations/Click-100k

Viewer • Updated Nov 11, 2025 • 101k • 841 • 18
🍨 Gelato-30B-A3B Checkpoints

Collection

Intermediate checkpoints for Gelato-30B-A3B. Refer to https://github.com/mlfoundations/gelato for more details. • 29 items • Updated Oct 29, 2025 • 1
mlfoundations/gelato-osworld-agent-trajectories

Viewer • Updated Nov 6, 2025 • 13.5k • 321 • 2

Pretrained ARC-Encoders and a fine-tuning dataset: context compression for unmodified LLMs.

ARC-Encoder: learning compressed text representations for large language models

Paper • 2510.20535 • Published Oct 23, 2025 • 10
kyutai/ARC8_Encoder_Llama

Feature Extraction • Updated Nov 5, 2025 • 12 • 3
kyutai/ARC_finetuning

Preview • Updated Oct 24, 2025 • 59 • 1
kyutai/ARC8_Encoder_multi

Feature Extraction • Updated Nov 5, 2025 • 54 • 7

High quality quants for Mac Studio (MLX)

Aiming to create the best quality quants for a single Mac Studio

mlx-community/GLM-5.2-DQ4plus-q8

Text Generation • 743B • Updated 3 days ago • 2.47k • 7
mlx-community/Kimi-K2.7-Code-mlx-DQ3_K_M-q8

Text Generation • 1T • Updated 4 days ago • 880 • 3
mlx-community/Kimi-K2.6-mlx-DQ3_K_M-q8

Text Generation • 1T • Updated Apr 21 • 100k • 8
mlx-community/GLM-5.1-DQ4plus-q8

Text Generation • 744B • Updated Apr 12 • 2.08k • 6

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 276
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks

Paper • 2510.08002 • Published Oct 9, 2025 • 24
Self-Improving LLM Agents at Test-Time

Paper • 2510.07841 • Published Oct 9, 2025 • 10
The Denario project: Deep knowledge AI agents for scientific discovery

Paper • 2510.26887 • Published Oct 30, 2025 • 8

Qwen3-VL-abliterated

huihui-ai/Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated

Image-Text-to-Text • 31B • Updated Dec 15, 2025 • 3.29k • 87
huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated Dec 15, 2025 • 9.09k • 68
huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated

Image-Text-to-Text • 9B • Updated Dec 15, 2025 • 17.1k • 185
huihui-ai/Huihui-Qwen3-VL-4B-Thinking-abliterated

Image-Text-to-Text • 4B • Updated Dec 15, 2025 • 103 • 28

t-tech/flex-sae

Updated Oct 27, 2025 • 1 • 12

Previous
1
...
42
43
44
45
46
...
21,244
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs