Smol Models - a BjornMelin Collection

BjornMelin 's Collections

Embedding Models

Single 4090 Laptop GPU

Legendary VL Models

Google

Llama

Qwen

LLMs

Smol Models

updated 5 days ago

My favorite smaller models under 10B parameters.

unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 16 • 256k • 295
nvidia/Llama-3.1-Nemotron-Nano-8B-v1

Text Generation • 8B • Updated May 8 • 209k • • 200
deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Text Generation • 8B • Updated Feb 24 • 820k • • 789
Qwen/Qwen2.5-Coder-7B-Instruct

Text Generation • 8B • Updated Jan 12 • 389k • • 532
Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12 • 11.3M • • 766
VIDraft/Gemma-3-R1984-4B

Image-Text-to-Text • 4B • Updated Apr 10 • 1.16k • 18
meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 13.3M • • 4.52k
meta-llama/Llama-3.2-3B-Instruct

Text Generation • 3B • Updated Oct 24, 2024 • 1.84M • • 1.67k
openbmb/MiniCPM-o-2_6

Any-to-Any • 9B • Updated Jun 20 • 194k • 1.22k
microsoft/Phi-4-mini-reasoning

Text Generation • 4B • Updated May 1 • 15.3k • 201
microsoft/bitnet-b1.58-2B-4T

Text Generation • 0.8B • Updated May 1 • 5.67k • 1.15k
microsoft/bitnet-b1.58-2B-4T-gguf

Text Generation • 2B • Updated May 1 • 4.3k • 194
unsloth/Qwen3-4B-Thinking-2507-GGUF

0.0B • Updated 20 days ago • 50.3k • 39
nvidia/NVIDIA-Nemotron-Nano-9B-v2

Text Generation • 9B • Updated about 12 hours ago • 36.4k • 242