Qwen/Qwen2.5-1.5B-Instruct
Text Generation
•
Updated
•
577k
•
296
Free Software Models
Only fully free software models as by definition: https://www.gnu.org/philosophy/free-sw.html
Note Runs as fastest on low-end hardware with 4 GB Nvidia GTX 1050 Ti GPU, and 16 GB RAM. It loads fully in GPU. About 50 tokens per second, too fast to read.
-
Qwen/Qwen2.5-0.5B-Instruct
Text Generation • Updated • 636k • • 197 -
Qwen/Qwen2.5-7B-Instruct-1M
Text Generation • Updated • 21.1k • 166 -
Qwen/Qwen2.5-32B-Instruct
Text Generation • Updated • 305k • 184 -
microsoft/Phi-3.5-mini-instruct
Text Generation • Updated • 1.14M • • 780 -
internlm/internlm3-8b-instruct
Text Generation • Updated • 33.3k • 189
allenai/OLMo-2-1124-7B
Updated • 29.7k • 43Note This is by Paul Allen!
-
ibm-granite/granite-3.1-2b-instruct
Text Generation • Updated • 17.2k • 31 -
microsoft/phi-4
Text Generation • Updated • 345k • 1.64k -
nomic-ai/modernbert-embed-base
Sentence Similarity • Updated • 92.5k • 181 -
cognitivecomputations/Dolphin3.0-Qwen2.5-1.5B
Updated • 267 • 7 -
anakin87/Phi-3.5-mini-ITA
Text Generation • Updated • 7.79k • 11 -
allenai/OLMo-2-1124-7B-Instruct-GGUF
Updated • 819 • 2 -
HuggingFaceTB/SmolVLM-500M-Instruct
Image-Text-to-Text • Updated • 10k • 87
DAMO-NLP-SG/VideoLLaMA3-7B
Visual Question Answering • Updated • 2.75k • 29Note Author named it "LLaMA3" for some unknown reason, I asked him why. It appears model is not base don LLaMA but on Qwen which was Apache 2.0 licensed. Once author responds, if there is no proprietary stuff inside, this note will be updated, or model removed from the list.
-
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Text Generation • Updated • 218k • 305 -
thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored
Updated • 440 • 8 -
microsoft/kosmos-2.5
Text2Text Generation • Updated • 4.18k • 184 -
microsoft/table-transformer-detection
Object Detection • Updated • 4.85M • 333 -
microsoft/Florence-2-large
Image-Text-to-Text • Updated • 433k • 1.38k -
microsoft/VidTok
Updated • 30 -
microsoft/DialoGPT-small
Text Generation • Updated • 39.5k • 117 -
microsoft/speecht5_tts
Text-to-Speech • Updated • 139k • 728 -
microsoft/cvt-13
Image Classification • Updated • 9.83k • 11 -
microsoft/trocr-large-handwritten
Image-to-Text • Updated • 416k • 103 -
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 3.02M • • 1.88k -
onnx-community/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 1.52k • 48 -
amazon/MistralLite-AWQ
Text Generation • Updated • 5 • 3 -
amazon/MegaBeam-Mistral-7B-300k
Text Generation • Updated • 6.18k • 15 -
Xenova/all-MiniLM-L6-v2
Feature Extraction • Updated • 296k • 56 -
TheBloke/Airoboros-M-7B-3.1.2-AWQ
Text Generation • Updated • 12 • 2 -
utter-project/EuroLLM-9B-Instruct
Text Generation • Updated • 21.4k • 140 -
mistralai/Mistral-Nemo-Instruct-2407
Text Generation • Updated • 1.43M • • 1.43k -
black-forest-labs/FLUX.1-schnell
Text-to-Image • Updated • 829k • • 3.32k -
google-bert/bert-large-cased
Fill-Mask • Updated • 106k • 32 -
mistralai/Mistral-Small-24B-Instruct-2501
Text Generation • Updated • 12.1k • • 491 -
TheBloke/Mixtral-8x7B-v0.1-GGUF
Updated • 4.84k • 424 -
01-ai/Yi-1.5-34B-Chat
Text Generation • Updated • 10.4k • • 265 -
nomic-ai/nomic-embed-text-v1.5
Sentence Similarity • Updated • 1.49M • 510 -
rubenroy/Zurich-14B-GCv2-5m
Text Generation • Updated • 32 • 6
