Bjorn Melin
BjornMelin
AI & ML interests
Large Language Models, AI Agents, Multi-Agent Orchestrations, Deep Learning, NLP, Local LLM Optimization.
Organizations
None yet
My favorite smaller models under 10B parameters.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 97.6k • 389 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • Updated • 304k • • 219 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • Updated • 851k • • 850 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1.98M • • 666
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 104k • 14 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • Updated • 4.34M • • 2.04k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.33M • • 5.57k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 111k • 33
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 17.7k • • 121 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 664k • 130 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 323 • • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 749k • • 613
-
smolagents LLM leaderboard
🏆141A leaderboard for LLMs powering smolagents
-
LLM Performance Leaderboard
🐨442View LLM performance leaderboard
-
Low-bit Quantized Open LLM Leaderboard
🏆195Track, rank and evaluate open LLMs and chatbots
-
UGI Leaderboard
📢1.58kUncensored General Intelligence Leaderboard
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 17.2k • 394 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 129k • 192 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.27M • • 1.92k -
google/gemma-3n-E4B-it
Image-Text-to-Text • Updated • 73.2k • • 880
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 17.7k • • 121 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 664k • 130 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 323 • • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 749k • • 613
-
smolagents LLM leaderboard
🏆141A leaderboard for LLMs powering smolagents
-
LLM Performance Leaderboard
🐨442View LLM performance leaderboard
-
Low-bit Quantized Open LLM Leaderboard
🏆195Track, rank and evaluate open LLMs and chatbots
-
UGI Leaderboard
📢1.58kUncensored General Intelligence Leaderboard
My favorite smaller models under 10B parameters.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 97.6k • 389 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • Updated • 304k • • 219 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • Updated • 851k • • 850 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1.98M • • 666
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 17.2k • 394 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 129k • 192 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.27M • • 1.92k -
google/gemma-3n-E4B-it
Image-Text-to-Text • Updated • 73.2k • • 880
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 104k • 14 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • Updated • 4.34M • • 2.04k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • Updated • 7.33M • • 5.57k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 111k • 33