Smol Models - a BjornMelin Collection

BjornMelin 's Collections

Embedding Models

Single 4090 Laptop GPU

Legendary VL Models

Google

Llama

Qwen

LLMs

Smol Models

updated Aug 22

My favorite smaller models under 10B parameters.

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

Text Generation • 8B • Updated Jun 16 • 49.4k • 343
nvidia/Llama-3.1-Nemotron-Nano-8B-v1

Text Generation • 8B • Updated Oct 15 • 8.69k • • 213
deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Text Generation • 8B • Updated Feb 24 • 982k • • 832
Qwen/Qwen2.5-Coder-7B-Instruct

Text Generation • 8B • Updated Jan 12 • 664k • • 572
Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12 • 6.96M • • 947
VIDraft/Gemma-3-R1984-4B

Image-Text-to-Text • 4B • Updated Apr 10 • 102 • 18
meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 8.78M • • 5.14k
meta-llama/Llama-3.2-3B-Instruct

Text Generation • 3B • Updated Oct 24, 2024 • 1.65M • • 1.87k
openbmb/MiniCPM-o-2_6

Any-to-Any • 9B • Updated Oct 5 • 101k • 1.27k
microsoft/Phi-4-mini-reasoning

Text Generation • 4B • Updated 5 days ago • 15.4k • 213
microsoft/bitnet-b1.58-2B-4T

Text Generation • 0.8B • Updated May 1 • 8.21k • 1.23k
microsoft/bitnet-b1.58-2B-4T-gguf

Text Generation • 2B • Updated May 1 • 3.34k • 215
unsloth/Qwen3-4B-Thinking-2507-GGUF

4B • Updated Sep 11 • 15.3k • 76
nvidia/NVIDIA-Nemotron-Nano-9B-v2

Text Generation • 9B • Updated 11 days ago • 72.2k • 451