Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation
•
Updated
•
144k
•
403
Smol Models
My favorite smaller models under 10B parameters.
-
-
Qwen/Qwen2.5-7B-Instruct
Text Generation • Updated • 1.17M • • 464 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 5.84M • • 3.58k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • Updated • 1.51M • • 957 -
google/gemma-2-9b-it
Text Generation • Updated • 396k • • 645 -
google/gemma-2-2b-it
Text Generation • Updated • 455k • • 931 -
openbmb/MiniCPM-o-2_6
Any-to-Any • Updated • 365k • 922 -
bartowski/DeepSeek-R1-Distill-Qwen-7B-GGUF
Text Generation • Updated • 493k • 58 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • Updated • 353k • 451 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • Updated • 218k • 337 -
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 248k • 2.7k