-
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 2.52M • 386 -
jinaai/jina-reranker-m0
Text Classification • 2B • Updated • 78.3k • 120 -
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 1.15M • 355 -
jinaai/jina-embeddings-v2-base-en
Feature Extraction • 0.1B • Updated • 83.2k • 736
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 • 56.4k • 442 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 174k • • 224 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 410k • • 873 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 2.15M • • 772
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 158k • 15 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.13M • • 2.43k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 7.46M • • 6.62k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 161k • 38
-
deepseek-ai/DeepSeek-V3
Text Generation • 685B • Updated • 1.1M • • 4.17k -
sentence-transformers/static-retrieval-mrl-en-v1
Sentence Similarity • Updated • 60 -
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 93.4k • 233 -
NovaSky-AI/Sky-T1-32B-Preview
Text Generation • 33B • Updated • 116 • • 550
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 851 • • 125 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 674k • 139 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 104 • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 818k • • 670
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 391 • 400 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 24k • 206 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 770k • • 2.01k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 30.2k • • 919
-
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 2.52M • 386 -
jinaai/jina-reranker-m0
Text Classification • 2B • Updated • 78.3k • 120 -
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 1.15M • 355 -
jinaai/jina-embeddings-v2-base-en
Feature Extraction • 0.1B • Updated • 83.2k • 736
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 851 • • 125 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 674k • 139 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 104 • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 818k • • 670
My favorite smaller models under 10B parameters.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 56.4k • 442 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 174k • • 224 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 410k • • 873 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 2.15M • • 772
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 391 • 400 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 24k • 206 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 770k • • 2.01k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 30.2k • • 919
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 158k • 15 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.13M • • 2.43k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 7.46M • • 6.62k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 161k • 38
-
deepseek-ai/DeepSeek-V3
Text Generation • 685B • Updated • 1.1M • • 4.17k -
sentence-transformers/static-retrieval-mrl-en-v1
Sentence Similarity • Updated • 60 -
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 93.4k • 233 -
NovaSky-AI/Sky-T1-32B-Preview
Text Generation • 33B • Updated • 116 • • 550