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

V-CoLA: Vision Token Compression with Linear Attention

Paper • 2610.11251 • Published 5 days ago • 12

joey234/mmlu-electrical_engineering-neg

Viewer • Updated Apr 20, 2023 • 145 • 19 • 3

Chat models in Outmake

The chat models Outmake lists for Macs, from 8 GB to 512 GB. Each runs on llama.cpp in the Outmake Mac app: outmake.app

unsloth/Qwen3.5-0.8B-GGUF

Image-Text-to-Text • 0.8B • Updated Mar 2 • 217k • 238
unsloth/Qwen3.5-2B-GGUF

Image-Text-to-Text • 2B • Updated Mar 2 • 362k • 164
unsloth/Qwen3.5-4B-GGUF

Image-Text-to-Text • 4B • Updated Mar 2 • 1.2M • 477
unsloth/Qwen3.5-9B-GGUF

Image-Text-to-Text • 9B • Updated Mar 2 • 1.22M • 986

Bharat-Embed: Hinglish Hindi retrieval family

270M text-only EmbeddingGemma-2 fork for Hinglish Hindi RAG. Weights, GGUF, legal adapter, triplets. Apache-2.0. By Eulogik.

eulogik/bharat-embed-270m-gemma2

Sentence Similarity • 0.3B • Updated 3 days ago • 44
eulogik/bharat-embed-270m-gemma2-GGUF

Feature Extraction • 0.3B • Updated 3 days ago • 241
eulogik/bharat-legal-embed-270m

Sentence Similarity • Updated 3 days ago
eulogik/bharat-embed-triplets-40k

Updated 4 days ago • 18

ex1-medbench-rl · MedAgentBench (experimental, WIP)

Experimental (WIP): Qwen3-0.6B as a FHIR agent on MedAgentBench; SFT warm-up then multi-turn GRPO. Not for clinical use.

prabakaranchandran/ex1-medbench-rl-medagent-sft-grpo-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 27

bartowski/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated 23 days ago • 476k • 204

Picture and video models in Outmake

The picture and video models Outmake lists. Each runs on stable-diffusion.cpp in the Outmake Mac app: outmake.app

leejet/Z-Image-Turbo-GGUF

Text-to-Image • 6B • Updated Dec 2, 2025 • 88.1k • 60
city96/FLUX.1-schnell-gguf

Text-to-Image • 12B • Updated Aug 18, 2024 • 118k • 361
QuantStack/Qwen-Image-GGUF

Text-to-Image • 20B • Updated Aug 6, 2025 • 27.9k • 51
QuantStack/Qwen-Image-Edit-2509-GGUF

Image-to-Image • 20B • Updated Oct 18, 2025 • 104k • 358

Running on Zero

MCP

11

Qwen Image 2.1 Turbo Studio

⚡

11

Qwen 2.1 Turbo, Simple/Pro, Qwen helper and LoRA library

nvidia/NV-Reason-CT

Image-Text-to-Text • 5B • Updated 18 days ago • 4.17k • 50

ex1-medbench-rl · MedCalc-Bench (experimental, WIP)

Experimental (WIP): Qwen3-0.6B on MedCalc-Bench Verified with GRPO and on-policy distillation (JAX). Not for clinical use.

prabakaranchandran/ex1-medbench-rl-medcalc-opd-lora-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 37
prabakaranchandran/ex1-medbench-rl-medcalc-grpo-lora-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 23

V-CoLA: Vision Token Compression with Linear Attention

Paper • 2610.11251 • Published 5 days ago • 12

bartowski/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated 23 days ago • 476k • 204

joey234/mmlu-electrical_engineering-neg

Viewer • Updated Apr 20, 2023 • 145 • 19 • 3

Picture and video models in Outmake

The picture and video models Outmake lists. Each runs on stable-diffusion.cpp in the Outmake Mac app: outmake.app

leejet/Z-Image-Turbo-GGUF

Text-to-Image • 6B • Updated Dec 2, 2025 • 88.1k • 60
city96/FLUX.1-schnell-gguf

Text-to-Image • 12B • Updated Aug 18, 2024 • 118k • 361
QuantStack/Qwen-Image-GGUF

Text-to-Image • 20B • Updated Aug 6, 2025 • 27.9k • 51
QuantStack/Qwen-Image-Edit-2509-GGUF

Image-to-Image • 20B • Updated Oct 18, 2025 • 104k • 358

Chat models in Outmake

The chat models Outmake lists for Macs, from 8 GB to 512 GB. Each runs on llama.cpp in the Outmake Mac app: outmake.app

unsloth/Qwen3.5-0.8B-GGUF

Image-Text-to-Text • 0.8B • Updated Mar 2 • 217k • 238
unsloth/Qwen3.5-2B-GGUF

Image-Text-to-Text • 2B • Updated Mar 2 • 362k • 164
unsloth/Qwen3.5-4B-GGUF

Image-Text-to-Text • 4B • Updated Mar 2 • 1.2M • 477
unsloth/Qwen3.5-9B-GGUF

Image-Text-to-Text • 9B • Updated Mar 2 • 1.22M • 986

Running on Zero

MCP

11

Qwen Image 2.1 Turbo Studio

⚡

11

Qwen 2.1 Turbo, Simple/Pro, Qwen helper and LoRA library

Bharat-Embed: Hinglish Hindi retrieval family

270M text-only EmbeddingGemma-2 fork for Hinglish Hindi RAG. Weights, GGUF, legal adapter, triplets. Apache-2.0. By Eulogik.

eulogik/bharat-embed-270m-gemma2

Sentence Similarity • 0.3B • Updated 3 days ago • 44
eulogik/bharat-embed-270m-gemma2-GGUF

Feature Extraction • 0.3B • Updated 3 days ago • 241
eulogik/bharat-legal-embed-270m

Sentence Similarity • Updated 3 days ago
eulogik/bharat-embed-triplets-40k

Updated 4 days ago • 18

nvidia/NV-Reason-CT

Image-Text-to-Text • 5B • Updated 18 days ago • 4.17k • 50

ex1-medbench-rl · MedAgentBench (experimental, WIP)

Experimental (WIP): Qwen3-0.6B as a FHIR agent on MedAgentBench; SFT warm-up then multi-turn GRPO. Not for clinical use.

prabakaranchandran/ex1-medbench-rl-medagent-sft-grpo-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 27

ex1-medbench-rl · MedCalc-Bench (experimental, WIP)

Experimental (WIP): Qwen3-0.6B on MedCalc-Bench Verified with GRPO and on-policy distillation (JAX). Not for clinical use.

prabakaranchandran/ex1-medbench-rl-medcalc-opd-lora-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 37
prabakaranchandran/ex1-medbench-rl-medcalc-grpo-lora-qwen3-0.6b

Text Generation • 0.6B • Updated 2 days ago • 23

Previous
1
...
118
119
120
121
122
...
23,915
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs