What open-source LLMs or SLMs are you in search of? 50723 in total.
Subscribe to LLM updates
Open-Source Language Model Lists by Categories
All Large Language Models LMSYS ChatBot Arena ELO OpenLLM LeaderBoard v1 OpenLLM LeaderBoard v2 Original & Foundation LLMs OpenCompass LeaderBoard Recently Added Models Code Generating Models Instruction-Based LLMs Uncensored LLMs LLMs Fit in 4GB RAM LLMs Fit in 8GB RAM LLMs Fit in 12GB RAM LLMs Fit in 24GB RAM LLMs Fit in 32GB RAM GGUF Quantized Models GPTQ Quantized Models EXL2 Quantized Models Fine-Tuned Models LLMs for Commercial Use TheBloke's Models Context Size >16K Tokens Mixture-Of-Experts Models Apple's MLX LLMs Small Language ModelsRecent LLM List
Model | Downloads | Likes | VRAM |
---|---|---|---|
Jan V1 4B janhq | 1756 | 250 | 8 |
Baichuan M2 32B baichuan-inc | 4096 | 72 | 65 |
Ling Lite 1.5 2507 inclusionAI | 93 | 63 | 33 |
Impish Nemo 12B SicariusSicariiStuff | 310 | 31 | 24 |
Gemma 3 270M It unsloth | 1488 | 5 | 0 |
...4B Thinking 2507 DAG Reasoning sequelbox | 8354 | 2 | 16 |
Gemma 3 270M It Qat MLX 4bit lmstudio-community | 1560 | 2 | 0 |
Gemma 3 270M It MLX 8bit lmstudio-community | 1461 | 2 | 0 |
Gemma 3 270M It MLX Bf16 lmstudio-community | 673 | 2 | 0 |
... All Pruned MoE Only 7 Experts AmanPriyanshu | 52 | 9 | 12 |
TOP 7b Param LLMs
Model | Downloads | Likes | VRAM |
---|---|---|---|
Qwen2.5 7B Instruct Qwen | 10596057 | 757 | 15 |
Qwen2.5 7B Instruct 1M Qwen | 1540462 | 346 | 15 |
Mistral 7B Instruct V0.2 mistralai | 3316095 | 2630 | 14 |
DeepSeek R1 Distill Qwen 7B deepseek-ai | 1704095 | 691 | 15 |
Qwen2.5 Omni 7B Qwen | 135688 | 1746 | 22 |
Janus Pro 7B deepseek-ai | 114486 | 3476 | 14 |
Zephyr 7B Beta HuggingFaceH4 | 706435 | 1757 | 14 |
Llama 2 7B Chat Hf meta-llama | 997200 | 4545 | 13 |
Mistral 7B Instruct V0.3 mistralai | 963522 | 2007 | 14 |
Gemma 7B It google | 97781 | 1203 | 17 |
TOP 34b Param LLMs
Model | Downloads | Likes | VRAM |
---|---|---|---|
Yi 1.5 34B Chat 01-ai | 12724 | 273 | 69 |
Yi 34B Chat 01-ai | 47661 | 356 | 69 |
Dolphin 2.9.1 Yi 1.5 34B cognitivecomputations | 4811054 | 37 | 69 |
YiSM Blossom5.1 34B SLERP CombinHorizon | 9236 | 0 | 69 |
YiSM 34B 0rn altomek | 17527 | 2 | 67 |
Falcon H1 34B Instruct tiiuae | 8456 | 43 | 67 |
Yi 1.5 34B 32K 01-ai | 11347 | 36 | 69 |
Blossom V5.1 34B Azure99 | 9997 | 5 | 68 |
Yi 1.5 34B Chat 16K 01-ai | 10037 | 27 | 69 |
Openbuddy Yi1.5 34B V21.3 32K OpenBuddy | 9206 | 0 | 69 |
LLMs Fit 16GB VRAM
Model | Downloads | Likes | VRAM |
---|---|---|---|
GPT Oss 20B openai | 3423894 | 3028 | 13 |
GPT Oss 20B GGUF unsloth | 506479 | 312 | 11 |
SmolLM3 3B HuggingFaceTB | 727050 | 661 | 6 |
Ministral 8B Instruct 2410 mistralai | 164675 | 516 | 16 |
Qwen3 4B Instruct 2507 Qwen | 126453 | 211 | 8 |
Llama 3.1 8B Instruct meta-llama | 14896283 | 4471 | 16 |
Qwen3 4B Thinking 2507 Qwen | 34268 | 294 | 8 |
Qwen2.5 7B Instruct Qwen | 10596057 | 757 | 15 |
Granite 3.1 8B Instruct ibm-granite | 36422 | 162 | 16 |
Hunyuan 1.8B Instruct tencent | 4892 | 590 | 3 |
TOP Code Generating LLMs
Model | Downloads | Likes | VRAM |
---|---|---|---|
Qwen2.5 Coder 32B Instruct Qwen | 76675 | 1918 | 65 |
Qwen3 Coder 30B A3B Instruct Qwen | 196373 | 468 | 61 |
Qwen3 Coder 480B A35B Instruct Qwen | 58716 | 1093 | 179 |
...3 Coder 480B A35B Instruct FP8 Qwen | 107139 | 99 | 439 |
...en3 Coder 30B A3B Instruct FP8 Qwen | 37510 | 53 | 31 |
Qwen2.5 Coder 7B Instruct Qwen | 262807 | 525 | 15 |
Qwen2.5 Coder 14B Instruct Qwen | 28244 | 124 | 29 |
ZYH LLM Qwen2.5 14B V4 YOYO-AI | 226 | 8 | 29 |
DeepSeek Coder V2 Instruct deepseek-ai | 7715 | 653 | 387 |
Sky T1 Coder 32B Flash tomasmcm | 11 | 2 | 65 |
Open-Source Language Model Lists by Benchmarks
LMSys ELOLMSys Chatbot Arena ELO RatingMMLU Pro
Mass. Multitask Language Understanding ProGPQA
General Purpose Question AnsweringMUSR
Multi-task Unified Skill RepresentationMATH Lvl 5
Mathematics Level 5BBH
Big Bench HardIFEval
Instruction Following EvaluationARC
Common Sense Reasoning, AccuracyHellaSwag
Sentence Completion, AccuracyMMLU
Multi-task Language Understanding, AverageTruthfulQA
Whether a model is truthful in generating answersWinoGrande
Common Sense Reasoning, AccuracyGSM8K
Arithmetic Reasoning, AccuracyHumanEval AVG
HumanEval for Multiple Languages, Pass@1Python Eval
HumanEval for Python, Pass@1Java Eval
HumanEval for Java, Pass@1Javascript Eval
HumanEval for Javascript, Pass@1CPP Eval
HumanEval for CPP, Pass@1PHP Eval
HumanEval for PHP, Pass@1Julia Eval
HumanEval for Julia, Pass@1D Eval
HumanEval for D, Pass@1Lua Eval
HumanEval for Lua, Pass@1R Eval
HumanEval for R, Pass@1Racket Eval
HumanEval for Racket, Pass@1Rust Eval
HumanEval for Rust, Pass@1Swift Eval
HumanEval for Swift, Pass@1OpenCompass Avg
OpenCompass Average ScoreExam
OpenCompass Examination ScoreLanguage
OpenCompass Language CapabilitiesKnowledge
OpenCompass Knowledge CapabilitiesUnderstanding
OpenCompass Understanding CapabilitiesReasoning
OpenCompass Reasoning CapabilitiesMTBench
Machine Translation, BLEUMATH Lvl 5
Mathematics Level 5LLME Score
LLM Explorer Score
About LLM Explorer
LLM Explorer: A platform connecting over 30,000 AI and ML professionals every month with the most recent Large Language Models, 50723 total. Offering an extensive collection of both large and small models, it's the go-to resource for the latest in AI advancements. With intuitive categorization, powerful analytics, and up-to-date benchmarks, it simplifies the search for the perfect language model for any business application. Whether you're an AI enthusiast, researcher, or industry professional, LLM Explorer is your essential guide to the dynamic landscape of language models.
Summary Statistics
Total LLMs | 50723 |
Quantized LLMs | 12147 |
Merged LLMs | 8674 |
Finetuned LLMs | 962 |
Uncensored LLMs | 933 |
Instruction-Based LLMs | 10863 |
Codegen LLMs | 1513 |
DB Last Update | 2025-08-17 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124