What open-source LLMs or SLMs are you in search of? 34044 in total.
Subscribe to LLM updates
Open-Source Language Model Lists by Categories
All Large Language Models LMSYS ChatBot Arena ELO Open LLM LeaderBoard Original & Foundation LLMs OpenCompass LeaderBoard Recently Added Models Trending LLMs & Hot Picks 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 ModelsMost Downloaded Weekly
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
Llama 3 Refueled refuelai | — | +700 | +82 | 16 |
Yi 1.5 34B Chat 01-ai | — | +1069 | +33 | 69 |
Llama3 70B Chinese Chat shenzhi-wang | — | +591 | +36 | 141 |
Sum Small omi-health | — | +88 | +35 | 7 |
ArrowPro 7B KUJIRA DataPilot | — | +1051 | +25 | 14 |
Llama3 Llava Next 8B lmms-lab | — | +1588 | +19 | 16 |
Llama 3 Sqlcoder 8B defog | — | +493 | +23 | 16 |
...a 3 8B Instruct Gradient 4194K gradientai | — | +1195 | +18 | 16 |
Llama 3 Cat 8B Instruct V1 TheSkullery | — | +80 | +21 | 16 |
Moistral 11B V4 TheDrummer | — | +44 | +21 | 21 |
Recent LLM List
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
EvoMerge1 Knobi3 | — | 101 | 2 | 14 |
Gemma 2B Coder MAISAAI | — | 2687 | 2 | 5 |
Llama 3 70B Instruct DPO V0.2 MaziyarPanahi | — | 458 | 2 | 141 |
Llama 3 70B Instruct DPO V0.3 MaziyarPanahi | — | 834 | 2 | 141 |
...hi 3 Context Obedient RAG GGUF MaziyarPanahi | — | 3938 | 2 | 1 |
Breeze 7B 32K Instruct V1.0 MediaTek-Research | — | 402 | 2 | 15 |
Mula 8x160 V0.1 MulaBR | — | 88 | 2 | 3 |
...1 2B It Orpo Traslate En Es V1 NickyNicky | — | 84 | 2 | 5 |
LuminRP 13B 128K Ppoyaa | — | 26 | 2 | 25 |
Mistral Supra TRI-ML | — | 566 | 2 | 31 |
TOP 7b Param LLMs
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
KAI 7B V0.1 Keynote-Technology | 74.45 | 34 | 9 | 14 |
Dolphin 2.2.1 Mistral 7B ehartford | 73.17 | 13484 | 185 | 14 |
...own Clown 7B Tak Stack DPO AWQ CorticalStack | 67 | 5 | 0 | 4 |
NeuralMonarch 7B AWQ solidrust | 66.9 | 5 | 0 | 4 |
AlphaHitchhiker 7B AWQ solidrust | 66.6 | 5 | 0 | 4 |
...ake 7B V2 Laser Truthy DPO AWQ macadeliccc | 66.1 | 5 | 0 | 4 |
Mistral 7B Instruct V0.2 mistralai | 65.71 | 2095986 | 2207 | 14 |
...andle Dolphin 2.2.1 Mistral 7B DanielClough | 64.2 | 249 | 0 | 14 |
Dolphin 2.8 Slerp AWQ solidrust | 63.4 | 5 | 0 | 4 |
Newton 7B 5.0bpw H6 EXL2 LoneStriker | 60.8 | 6 | 0 | 4 |
TOP 34b Param LLMs
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
SUS Chat 34B SUSTech | 85.03 | 4784 | 115 | 68 |
Yi 34B 01-ai | 79.53 | 10878 | 1251 | 68 |
SUS Chat 34B GPTQ TheBloke | 74.6 | 2 | 3 | 18 |
SUS Chat 34B AWQ TheBloke | 74.6 | 37 | 9 | 19 |
SUS Chat 34B GGUF TheBloke | 74.6 | 809 | 16 | 14 |
OrionStar Yi 34B Chat OrionStarAI | 72.62 | 46 | 60 | 68 |
...Hermes 2 Yi 34B 6.0bpw H6 EXL2 LoneStriker | 69.7 | 5 | 0 | 26 |
...ermes 2 Yi 34B 4.65bpw H6 EXL2 LoneStriker | 69.7 | 4 | 1 | 20 |
...Hermes 2 Yi 34B 5.0bpw H6 EXL2 LoneStriker | 69.7 | 5 | 1 | 22 |
...Hermes 2 Yi 34B 3.0bpw H6 EXL2 LoneStriker | 69.7 | 6 | 2 | 13 |
LLMs Fit 16GB VRAM
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
SUS Chat 34B GGUF TheBloke | 74.6 | 809 | 16 | 14 |
KAI 7B V0.1 Keynote-Technology | 74.45 | 34 | 9 | 14 |
Dolphin 2.2.1 Mistral 7B ehartford | 73.17 | 13484 | 185 | 14 |
...Hermes 2 Yi 34B 3.0bpw H6 EXL2 LoneStriker | 69.7 | 6 | 2 | 13 |
Yi 34B GGUF TheBloke | 69.7 | 1797 | 73 | 14 |
Phi3 4K ehartford | 69.6 | 11 | 0 | 7 |
...own Clown 7B Tak Stack DPO AWQ CorticalStack | 67 | 5 | 0 | 4 |
NeuralMonarch 7B AWQ solidrust | 66.9 | 5 | 0 | 4 |
AlphaHitchhiker 7B AWQ solidrust | 66.6 | 5 | 0 | 4 |
...ake 7B V2 Laser Truthy DPO AWQ macadeliccc | 66.1 | 5 | 0 | 4 |
TOP Code Generating LLMs
Model | Score | Downloads | Likes | VRAM |
---|---|---|---|---|
Nxcode CQ 7B Orpo NTQAI | 87.23 | 473 | 20 | 14 |
CodeQwen1.5 7B Chat Qwen | 87.2 | 18530 | 158 | 14 |
Deepseek Coder 6.7B Instruct deepseek-ai | 80.22 | 98138 | 296 | 13 |
Deepseek Coder 33B Instruct deepseek-ai | 80.02 | 20644 | 397 | 66 |
CodeFuse DeepSeek 33B codefuse-ai | 76.83 | 142 | 53 | 66 |
CodeQwen1.5 7B AWQ TechxGenus | 76.7 | 57 | 0 | 4 |
CodeQwen1.5 7B Chat GGUF second-state | 76.7 | 1298 | 0 | 5 |
CodeQwen1.5 7B AWQ Qwen | 76.7 | 267 | 2 | 5 |
...odeQwen1.5 7B Chat EXL2 8.0bpw Dracones | 76.7 | 10 | 4 | 7 |
CodeQwen1.5 7B Chat AWQ Qwen | 76.7 | 656 | 4 | 5 |
Open-Source Language Model Lists by Benchmarks
LMSys ELOLMSys Chatbot Arena ELO RatingHF Avg Score
HuggingFace OpenLLM LeaderBoard ScoreARC
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, BLEU
About LLM Explorer
LLM Explorer: A platform connecting over 30,000 AI and ML professionals every month with the most recent Large Language Models, 34044 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 | 34044 |
Quantized LLMs | 9083 |
Merged LLMs | 3852 |
Finetuned LLMs | 803 |
Uncensored LLMs | 284 |
Instruction-Based LLMs | 4855 |
Codegen LLMs | 941 |
DB Last Update | 2024-05-14 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801