-
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 1.54M • 408 -
jinaai/jina-reranker-m0
Text Classification • 2B • Updated • 39.9k • 120 -
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 987k • 358 -
jinaai/jina-embeddings-v2-base-en
Feature Extraction • 0.1B • Updated • 359k • 738
Bjorn Melin
BjornMelin
AI & ML interests
Large Language Models, AI Agents, Multi-Agent Orchestrations, Deep Learning, NLP, Local LLM Optimization.
Organizations
None yet
Datasets
Fine Tuning
- Running94
GGUF Model VRAM Calculator
📈94Calculate VRAM requirements for LLM models
- Running on CPU UpgradeAgentsFeatured1.02k
Model Memory Utility
🚀1.02kCalculate GPU memory needed for training Hugging Face models
- RunningFeatured1.05k
Can You Run It? LLM version
🚀1.05kCheck if your GPU can run a chosen LLM model
Legendary VL Models
Smol Models
My favorite smaller models under 10B parameters.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 97.2k • 464 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 7.26k • • 224 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 164k • • 884 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1.78M • • 820
Llama
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 131k • 15 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.49M • • 2.77k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 5.93M • • 8.33k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 138k • 40
LLMs
-
deepseek-ai/DeepSeek-V3
Text Generation • 685B • Updated • 1.46M • • 4.4k -
sentence-transformers/static-retrieval-mrl-en-v1
Sentence Similarity • Updated • 61 -
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 65.9k • 235 -
NovaSky-AI/Sky-T1-32B-Preview
Text Generation • 33B • Updated • 249 • • 549
Embedding Models
Single 4090 Laptop GPU
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 756 • • 125 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 950k • 140 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 132 • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 328k • • 701
Leaderboards
- Runtime errorFeatured142
smolagents LLM leaderboard
🏆142A leaderboard for LLMs powering smolagents
- RunningFeatured493
LLM Performance Leaderboard
🐨493View the LLM leaderboard rankings
- RunningAgentsFeatured230
Low-bit LLM Leaderboard
🏆230Track, rank and evaluate open LLMs and chatbots
- Running2.12k
UGI Leaderboard
📢2.12kUncensored General Intelligence Leaderboard
Coding Models
Google
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 348 • 406 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 38.4k • 207 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 417k • • 2.05k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 12.2k • • 931
Qwen
Rerankers
-
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 1.54M • 408 -
jinaai/jina-reranker-m0
Text Classification • 2B • Updated • 39.9k • 120 -
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 987k • 358 -
jinaai/jina-embeddings-v2-base-en
Feature Extraction • 0.1B • Updated • 359k • 738
Embedding Models
Datasets
Single 4090 Laptop GPU
-
nvidia/OpenReasoning-Nemotron-32B
Text Generation • 33B • Updated • 756 • • 125 -
Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 950k • 140 -
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 132 • 392 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text Generation • 15B • Updated • 328k • • 701
Fine Tuning
- Running94
GGUF Model VRAM Calculator
📈94Calculate VRAM requirements for LLM models
- Running on CPU UpgradeAgentsFeatured1.02k
Model Memory Utility
🚀1.02kCalculate GPU memory needed for training Hugging Face models
- RunningFeatured1.05k
Can You Run It? LLM version
🚀1.05kCheck if your GPU can run a chosen LLM model
Leaderboards
- Runtime errorFeatured142
smolagents LLM leaderboard
🏆142A leaderboard for LLMs powering smolagents
- RunningFeatured493
LLM Performance Leaderboard
🐨493View the LLM leaderboard rankings
- RunningAgentsFeatured230
Low-bit LLM Leaderboard
🏆230Track, rank and evaluate open LLMs and chatbots
- Running2.12k
UGI Leaderboard
📢2.12kUncensored General Intelligence Leaderboard
Legendary VL Models
Coding Models
Smol Models
My favorite smaller models under 10B parameters.
-
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
Text Generation • 8B • Updated • 97.2k • 464 -
nvidia/Llama-3.1-Nemotron-Nano-8B-v1
Text Generation • 8B • Updated • 7.26k • • 224 -
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text Generation • 8B • Updated • 164k • • 884 -
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1.78M • • 820
Google
-
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 348 • 406 -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 38.4k • 207 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 417k • • 2.05k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 12.2k • • 931
Llama
-
MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF
Text Generation • 3B • Updated • 131k • 15 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 1.49M • • 2.77k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 5.93M • • 8.33k -
MaziyarPanahi/Meta-Llama-3.1-8B-Instruct-GGUF
Text Generation • 8B • Updated • 138k • 40
Qwen
LLMs
-
deepseek-ai/DeepSeek-V3
Text Generation • 685B • Updated • 1.46M • • 4.4k -
sentence-transformers/static-retrieval-mrl-en-v1
Sentence Similarity • Updated • 61 -
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 65.9k • 235 -
NovaSky-AI/Sky-T1-32B-Preview
Text Generation • 33B • Updated • 249 • • 549