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

9B Dense MTP Vision for 12–16 GB GPUs

Small 9B agents in EXL3: 6.00bpw for 16 GB, 4.50bpw branch for 12 GB. Tested on real sysadmin tasks in Spanish with opencode.

JRamirez-UAB/Ornith-1.5-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 245
JRamirez-UAB/NeoHorse-1-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 165

Sysadmin agent models: our picks

What we actually run, one per GPU size, for a Spanish-language Linux sysadmin agent with opencode.

JRamirez-UAB/Ornith-1.5-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 245
JRamirez-UAB/Swift-1.5-Qwen3.8-27B-EXL3-3.85bpw-24GB

Image-Text-to-Text • 8B • Updated 2 days ago • 384 • 2
JRamirez-UAB/Ornith-1.5-35B-A3B-EXL3-4.00bpw-24GB

Image-Text-to-Text • 10B • Updated 3 days ago • 224
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 151

YOLOX-Nano · person · STM32N6

INT8 person detectors for the STM32N6, st_yoloxn I/O. Modified from Megvii YOLOX-Nano.

FasterAI-Labs/yolox-nano-person-stm32n6

Object Detection • Updated 5 days ago

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-EXL3-2.9bpw

Image-Text-to-Text • 105B • Updated Sep 17 • 1.78k • 46

TandemLLM LFM2.5-24B-A2B EXL3

EXL3 quants of Liquid AI's LFM2.5-24B-A2B, 2.5 to 6.0 bpw, made with exllamav3 1.6.0 for TandemLLM 0.9.0. LFM Open License v1.0.

0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-2.5

Text Generation • 4B • Updated 5 days ago • 80 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-3.0

Text Generation • 5B • Updated 5 days ago • 77 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-3.5

Text Generation • 6B • Updated 5 days ago • 83 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-4.0

Text Generation • 6B • Updated 5 days ago • 78 • 1

120-125B MoE Vision for 48-96 GB GPUs

Large MoE in EXL3 for 48-96 GB: Qwen3.8 Flash-Next (125B-A6B, MTP) and NVIDIA Nemotron-3.5-Super-VL (120B-A12B, vision, 1M ctx). vLLM Blackwell.

about 11 hours ago

JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 151
JRamirez-UAB/Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 137
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-3.75bpw-96GB

Image-Text-to-Text • 32B • Updated 3 days ago • 107
JRamirez-UAB/Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.25bpw-VL-48-96GB

Image-Text-to-Text • 19B • Updated about 9 hours ago

PlantNet SSL models (embeddings)

Pl@ntNet self-supervised vision models trained on large-scale plant image datasets for transferable visual representations (output=embeddings).

PlantNet/simdinov2-vit-large-pn22m-in1k

Image Feature Extraction • 0.3B • Updated Sep 17 • 17 • 1

Running on Zero

Agents

165

Qwen Image Edit NSFW

🖼

165

Uncensored Image editing tool Edit image with a text prompt

fishaudio/drama-3

Text-to-Speech • 36B • Updated 2 days ago • 9.62k • 709

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 19 days ago • 70
Agent-Reflex: Teaching Language Agents to Act Reflectively

Paper • 2610.17953 • Published 6 days ago • 213

9B Dense MTP Vision for 12–16 GB GPUs

Small 9B agents in EXL3: 6.00bpw for 16 GB, 4.50bpw branch for 12 GB. Tested on real sysadmin tasks in Spanish with opencode.

JRamirez-UAB/Ornith-1.5-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 245
JRamirez-UAB/NeoHorse-1-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 165

120-125B MoE Vision for 48-96 GB GPUs

Large MoE in EXL3 for 48-96 GB: Qwen3.8 Flash-Next (125B-A6B, MTP) and NVIDIA Nemotron-3.5-Super-VL (120B-A12B, vision, 1M ctx). vLLM Blackwell.

about 11 hours ago

JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 151
JRamirez-UAB/Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 137
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-3.75bpw-96GB

Image-Text-to-Text • 32B • Updated 3 days ago • 107
JRamirez-UAB/Nemotron-3.5-Super-VL-120B-A12B-EXL3-2.25bpw-VL-48-96GB

Image-Text-to-Text • 19B • Updated about 9 hours ago

Sysadmin agent models: our picks

What we actually run, one per GPU size, for a Spanish-language Linux sysadmin agent with opencode.

JRamirez-UAB/Ornith-1.5-9B-EXL3-16GB-12GB

Image-Text-to-Text • 4B • Updated 3 days ago • 245
JRamirez-UAB/Swift-1.5-Qwen3.8-27B-EXL3-3.85bpw-24GB

Image-Text-to-Text • 8B • Updated 2 days ago • 384 • 2
JRamirez-UAB/Ornith-1.5-35B-A3B-EXL3-4.00bpw-24GB

Image-Text-to-Text • 10B • Updated 3 days ago • 224
JRamirez-UAB/Swift-1.5-Qwen3.8-Flash-Next-EXL3-2.25bpw-48GB

Image-Text-to-Text • 20B • Updated 3 days ago • 151

PlantNet SSL models (embeddings)

Pl@ntNet self-supervised vision models trained on large-scale plant image datasets for transferable visual representations (output=embeddings).

PlantNet/simdinov2-vit-large-pn22m-in1k

Image Feature Extraction • 0.3B • Updated Sep 17 • 17 • 1

YOLOX-Nano · person · STM32N6

INT8 person detectors for the STM32N6, st_yoloxn I/O. Modified from Megvii YOLOX-Nano.

FasterAI-Labs/yolox-nano-person-stm32n6

Object Detection • Updated 5 days ago

Running on Zero

Agents

165

Qwen Image Edit NSFW

🖼

165

Uncensored Image editing tool Edit image with a text prompt

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-EXL3-2.9bpw

Image-Text-to-Text • 105B • Updated Sep 17 • 1.78k • 46

fishaudio/drama-3

Text-to-Speech • 36B • Updated 2 days ago • 9.62k • 709

TandemLLM LFM2.5-24B-A2B EXL3

EXL3 quants of Liquid AI's LFM2.5-24B-A2B, 2.5 to 6.0 bpw, made with exllamav3 1.6.0 for TandemLLM 0.9.0. LFM Open License v1.0.

0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-2.5

Text Generation • 4B • Updated 5 days ago • 80 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-3.0

Text Generation • 5B • Updated 5 days ago • 77 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-3.5

Text Generation • 6B • Updated 5 days ago • 83 • 1
0xBakeer/TandemLLM-LFM2.5-24B-A2B-EXL3-4.0

Text Generation • 6B • Updated 5 days ago • 78 • 1

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 19 days ago • 70
Agent-Reflex: Teaching Language Agents to Act Reflectively

Paper • 2610.17953 • Published 6 days ago • 213

Previous
1
...
197
198
199
200
201
...
24,099
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs