all-minilm | 22m | Dec/2023 | Sentence Transformers | Germany | 8 GB | 4 GB | 1 GB | Natural Language Understanding,Data Analysis |
all-minilm | 33m | Dec/2023 | Sentence Transformers | Germany | 8 GB | 4 GB | 1 GB | Natural Language Understanding,Data Analysis |
alfred | 40b | Dec/2023 | | Unknown | 64 GB | 32 GB | 22 GB | Text Generation,Natural Language Understanding |
athene-v2 | 72b | Nov/2024 | | Unknown | 128 GB | 64 GB | 39 GB | Text Generation,Natural Language Understanding |
aya | 8b | Jan/2024 | Cohere | Canada | 16 GB | 8 GB | 4 GB | Text Generation,Natural Language Understanding,Machine Translation |
aya | 35b | Jan/2024 | Cohere | Canada | 64 GB | 32 GB | 19 GB | Text Generation,Natural Language Understanding,Machine Translation |
aya-expanse | 8b | Jun/2024 | Cohere | Canada | 16 GB | 8 GB | 4 GB | Text Generation,Natural Language Understanding,Machine Translation |
aya-expanse | 32b | Jun/2024 | Cohere | Canada | 64 GB | 32 GB | 17 GB | Text Generation,Natural Language Understanding,Machine Translation |
bakllava | 7b | Dec/2023 | Skunkworks AI | USA | 16 GB | 8 GB | 4 GB | Image Classification,Natural Language Understanding |
bespoke-minicheck | 7b | Jul/2024 | Bespoke Labs | USA | 16 GB | 8 GB | 4 GB | |
bge-large | 335m | Jan/2024 | BAAI | China | 8 GB | 4 GB | 1 GB | |
bge-m3 | 567m | Jan/2024 | BAAI | China | 8 GB | 4 GB | 1 GB | |
codebooga | 34b | Dec/2023 | TheBloke (Independent) | UK | 64 GB | 32 GB | 18 GB | |
codegemma | 2b | Mar/2024 | Google DeepMind | UK | 8 GB | 4 GB | 1 GB | |
codegemma | 7b | Mar/2024 | Google DeepMind | UK | 16 GB | 8 GB | 4 GB | |
codeqwen | 7b | Oct/2023 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
codeqeex4 | 9b | Jun/2024 | xAI | USA | 16 GB | 8 GB | 5 GB | |
codellama | 7b | Jul/2023 | Meta AI | USA | 16 GB | 8 GB | 4 GB | |
codellama | 13b | Jul/2023 | Meta AI | USA | 16 GB | 8 GB | 7 GB | |
codellama | 34b | Jul/2023 | Meta AI | USA | 64 GB | 32 GB | 18 GB | |
codellama | 70b | Jul/2023 | Meta AI | USA | 128 GB | 64 GB | 38 GB | |
codestral | 22b | Apr/2024 | Mistral AI | France | 32 GB | 16 GB | 12 GB | |
codeup | 13b | Dec/2023 | DeepSE | Unknown | 16 GB | 8 GB | 7 GB | |
cogito | 3b | Nov/2024 | Deep Cogito | USA | 8 GB | 4 GB | 2 GB | |
cogito | 8b | Nov/2024 | Deep Cogito | USA | 16 GB | 8 GB | 4 GB | |
cogito | 14b | Nov/2024 | Deep Cogito | USA | 16 GB | 8 GB | 8 GB | |
cogito | 32b | Nov/2024 | Deep Cogito | USA | 64 GB | 32 GB | 17 GB | |
cogito | 70b | Nov/2024 | Deep Cogito | USA | 128 GB | 64 GB | 38 GB | |
command-a | 111b | Feb/2025 | Cohere | Canada | 128 GB | 64 GB | 60 GB | |
command-r | 35b | Feb/2024 | Cohere | Canada | 64 GB | 32 GB | 19 GB | |
command-r-plus | 104b | Mar/2024 | Cohere | Canada | 128 GB | 64 GB | 56 GB | |
command-r7b | 7b | Feb/2025 | Cohere | Canada | 16 GB | 8 GB | 4 GB | |
command-r7b-arabic | 7b | Feb/2025 | Cohere | Canada | 16 GB | 8 GB | 4 GB | |
dbrx | 132b | Feb/2024 | Databricks | USA | 128 GB | 64 GB | 71 GB | |
deepcoder | 1.5b | Nov/2024 | | Unknown | 8 GB | 4 GB | 1 GB | |
deepcoder | 14b | Nov/2024 | | Unknown | 16 GB | 8 GB | 8 GB | |
deepseek-coder | 1.3b | Dec/2023 | DeepSeek | China | 8 GB | 4 GB | 1 GB | |
deepseek-coder | 6.7b | Dec/2023 | DeepSeek | China | 16 GB | 8 GB | 4 GB | |
deepseek-coder | 33b | Dec/2023 | DeepSeek | China | 64 GB | 32 GB | 18 GB | |
deepseek-coder-v2 | 16b | May/2024 | DeepSeek | China | 32 GB | 16 GB | 9 GB | |
deepseek-coder-v2 | 236b | May/2024 | DeepSeek | China | 128 GB | 64 GB | 127 GB | |
deepseek-llm | 7b | Dec/2023 | DeepSeek | China | 16 GB | 8 GB | 4 GB | |
deepseek-llm | 67b | Dec/2023 | DeepSeek | China | 128 GB | 64 GB | 36 GB | |
deepseek-r1 | 1.5b | Apr/2025 | DeepSeek | China | 8 GB | 4 GB | 1 GB | |
deepseek-r1 | 7b | Apr/2025 | DeepSeek | China | 16 GB | 8 GB | 4 GB | |
deepseek-r1 | 8b | Apr/2025 | DeepSeek | China | 16 GB | 8 GB | 4 GB | |
deepseek-r1 | 14b | Apr/2025 | DeepSeek | China | 16 GB | 8 GB | 8 GB | |
deepseek-r1 | 32b | Apr/2025 | DeepSeek | China | 64 GB | 32 GB | 17 GB | |
deepseek-r1 | 70b | Apr/2025 | DeepSeek | China | 128 GB | 64 GB | 38 GB | |
deepseek-r1 | 671b | Apr/2025 | DeepSeek | China | 128 GB | 64 GB | 362 GB | |
deepseek-v2 | 16b | Apr/2024 | DeepSeek | China | 32 GB | 16 GB | 9 GB | |
deepseek-v2.5 | 236b | Jul/2024 | DeepSeek | China | 128 GB | 64 GB | 127 GB | |
deepseek-v3 | 671b | Oct/2024 | DeepSeek | China | 128 GB | 64 GB | 362 GB | |
deepscaler | 1.5b | Feb/2025 | DeepSeek | China | 8 GB | 4 GB | 1 GB | |
devstral | 24b | Apr/2025 | xAI | USA | 32 GB | 16 GB | 13 GB | |
dolphin-llama3 | 8b | Mar/2024 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
dolphin-llama3 | 70b | Mar/2024 | Eric Hartford (Independent) | USA | 128 GB | 64 GB | 38 GB | |
dolphin-mistral | 7b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
dolphin-mixtral | 8x7b | Mar/2024 | Eric Hartford (Independent) | USA | 64 GB | 32 GB | 4 GB | |
dolphin-mixtral | 8x22b | Mar/2024 | Eric Hartford (Independent) | USA | 128 GB | 64 GB | 12 GB | |
dolphin-phi | 2.7b | Dec/2023 | Microsoft | USA | 8 GB | 4 GB | 1 GB | |
dolphin3 | 8b | Mar/2024 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
dolphincoder | 7b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
dolphincoder | 15b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 8 GB | |
duckdb-nsql | 7b | Dec/2023 | MotherDuck | USA | 16 GB | 8 GB | 4 GB | |
everythinglm | 13b | Dec/2023 | | Unknown | 16 GB | 8 GB | 7 GB | |
exaone3.5 | 2.4b | Jan/2024 | LG AI Research | South Korea | 8 GB | 4 GB | 1 GB | |
exaone3.5 | 7.8b | Jan/2024 | LG AI Research | South Korea | 16 GB | 8 GB | 4 GB | |
exaone3.5 | 32b | Jan/2024 | LG AI Research | South Korea | 64 GB | 32 GB | 17 GB | |
exaone-deep | 2.4b | Mar/2025 | LG AI Research | South Korea | 8 GB | 4 GB | 1 GB | |
exaone-deep | 7.8b | Mar/2025 | LG AI Research | South Korea | 16 GB | 8 GB | 4 GB | |
exaone-deep | 32b | Mar/2025 | LG AI Research | South Korea | 64 GB | 32 GB | 17 GB | |
falcon | 7b | Feb/2023 | Technology Innovation Institute | UAE | 16 GB | 8 GB | 4 GB | |
falcon | 40b | Feb/2023 | Technology Innovation Institute | UAE | 64 GB | 32 GB | 22 GB | |
falcon | 180b | Feb/2023 | Technology Innovation Institute | UAE | 128 GB | 64 GB | 97 GB | |
falcon2 | 11b | Apr/2024 | Technology Innovation Institute | UAE | 16 GB | 8 GB | 6 GB | |
falcon3 | 1b | Feb/2024 | Technology Innovation Institute | UAE | 8 GB | 4 GB | 1 GB | |
falcon3 | 3b | Feb/2024 | Technology Innovation Institute | UAE | 8 GB | 4 GB | 2 GB | |
falcon3 | 7b | Feb/2024 | Technology Innovation Institute | UAE | 16 GB | 8 GB | 4 GB | |
falcon3 | 10b | Feb/2024 | Technology Innovation Institute | UAE | 16 GB | 8 GB | 5 GB | |
firefunction-v2 | 70b | Jul/2024 | | Unknown | 128 GB | 64 GB | 38 GB | |
gemma | 2b | Jan/2024 | Google DeepMind | UK | 8 GB | 4 GB | 1 GB | |
gemma | 7b | Jan/2024 | Google DeepMind | UK | 16 GB | 8 GB | 4 GB | |
gemma2 | 2b | May/2024 | Google DeepMind | UK | 8 GB | 4 GB | 1 GB | |
gemma2 | 9b | May/2024 | Google DeepMind | UK | 16 GB | 8 GB | 5 GB | |
gemma2 | 27b | May/2024 | Google DeepMind | UK | 32 GB | 16 GB | 15 GB | |
gemma3 | 1b | Mar/2025 | Google DeepMind | UK | 8 GB | 4 GB | 1 GB | |
gemma3 | 4b | Mar/2025 | Google DeepMind | UK | 8 GB | 4 GB | 2 GB | |
gemma3 | 12b | Mar/2025 | Google DeepMind | UK | 16 GB | 8 GB | 6 GB | |
gemma3 | 27b | Mar/2025 | Google DeepMind | UK | 32 GB | 16 GB | 15 GB | |
glm4 | 9b | Jun/2024 | Tsinghua KEG | China | 16 GB | 8 GB | 5 GB | |
goliath | 120b | Dec/2023 | | Unknown | 128 GB | 64 GB | 65 GB | |
granite-code | 3b | Apr/2024 | IBM | USA | 8 GB | 4 GB | 2 GB | |
granite-code | 8b | Apr/2024 | IBM | USA | 16 GB | 8 GB | 4 GB | |
granite-code | 20b | Apr/2024 | IBM | USA | 32 GB | 16 GB | 11 GB | |
granite-code | 34b | Apr/2024 | IBM | USA | 64 GB | 32 GB | 18 GB | |
granite-embedding | 30m | Feb/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite-embedding | 278m | Feb/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3-dense | 2b | Dec/2023 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3-dense | 8b | Dec/2023 | IBM | USA | 16 GB | 8 GB | 4 GB | |
granite3-moe | 1b | Dec/2023 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3-moe | 3b | Dec/2023 | IBM | USA | 8 GB | 4 GB | 2 GB | |
granite3.1-dense | 2b | Feb/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3.1-dense | 8b | Feb/2024 | IBM | USA | 16 GB | 8 GB | 4 GB | |
granite3.1-moe | 1b | Feb/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3.1-moe | 3b | Feb/2024 | IBM | USA | 8 GB | 4 GB | 2 GB | |
granite3.2 | 2b | Mar/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3.2 | 8b | Mar/2024 | IBM | USA | 16 GB | 8 GB | 4 GB | |
granite3.2-vision | 2b | Mar/2024 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3.3 | 2b | Mar/2025 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3.3 | 8b | Mar/2025 | IBM | USA | 16 GB | 8 GB | 4 GB | |
granite3-guardian | 2b | Dec/2023 | IBM | USA | 8 GB | 4 GB | 1 GB | |
granite3-guardian | 8b | Dec/2023 | IBM | USA | 16 GB | 8 GB | 4 GB | |
hermes3 | 3b | Jul/2024 | Nous Research | USA | 8 GB | 4 GB | 2 GB | |
hermes3 | 8b | Jul/2024 | Nous Research | USA | 16 GB | 8 GB | 4 GB | |
hermes3 | 70b | Jul/2024 | Nous Research | USA | 128 GB | 64 GB | 38 GB | |
hermes3 | 405b | Jul/2024 | Nous Research | USA | 128 GB | 64 GB | 219 GB | |
internlm2 | 1m | Jun/2024 | Shanghai AI Laboratory | China | 8 GB | 4 GB | 1 GB | |
internlm2 | 1.8b | Jun/2024 | Shanghai AI Laboratory | China | 8 GB | 4 GB | 1 GB | |
internlm2 | 7b | Jun/2024 | Shanghai AI Laboratory | China | 16 GB | 8 GB | 4 GB | |
internlm2 | 20b | Jun/2024 | Shanghai AI Laboratory | China | 32 GB | 16 GB | 11 GB | |
llama-pro | Unknown | Dec/2023 | | Unknown | 8 GB | 4 GB | 1 GB | |
llama2 | 7b | Jun/2023 | Meta AI | USA | 16 GB | 8 GB | 4 GB | |
llama2 | 13b | Jun/2023 | Meta AI | USA | 16 GB | 8 GB | 7 GB | |
llama2 | 70b | Jun/2023 | Meta AI | USA | 128 GB | 64 GB | 38 GB | |
llama2-chinese | 7b | Jun/2023 | Chinese-LLaMA-Alpaca Team | China | 16 GB | 8 GB | 4 GB | |
llama2-chinese | 13b | Jun/2023 | Chinese-LLaMA-Alpaca Team | China | 16 GB | 8 GB | 7 GB | |
llama2-uncensored | 7b | Jul/2023 | George Sung (Independent) | USA | 16 GB | 8 GB | 4 GB | |
llama2-uncensored | 70b | Jul/2023 | George Sung (Independent) | USA | 128 GB | 64 GB | 38 GB | |
llama3 | 8b | Mar/2024 | Meta AI | USA | 16 GB | 8 GB | 4 GB | |
llama3 | 70b | Mar/2024 | Meta AI | USA | 128 GB | 64 GB | 38 GB | |
llama3-chatqa | 8b | Jun/2024 | NVIDIA | USA | 16 GB | 8 GB | 4 GB | |
llama3-chatqa | 70b | Jun/2024 | NVIDIA | USA | 128 GB | 64 GB | 38 GB | |
llama3-gradient | 8b | May/2024 | | USA | 16 GB | 8 GB | 4 GB | |
llama3-gradient | 70b | May/2024 | | USA | 128 GB | 64 GB | 38 GB | |
llama3-groq-tool-use | 8b | Jul/2024 | Groq | USA | 16 GB | 8 GB | 4 GB | |
llama3-groq-tool-use | 70b | Jul/2024 | Groq | USA | 128 GB | 64 GB | 38 GB | |
llama3.1 | 8b | Jun/2024 | Meta AI | USA | 16 GB | 8 GB | 4 GB | |
llama3.1 | 70b | Jun/2024 | Meta AI | USA | 128 GB | 64 GB | 38 GB | |
llama3.1 | 405b | Jun/2024 | Meta AI | USA | 128 GB | 64 GB | 219 GB | |
llama3.2 | 1b | Jun/2025 | Meta AI | USA | 8 GB | 4 GB | 1 GB | |
llama3.2 | 3b | Jun/2025 | Meta AI | USA | 8 GB | 4 GB | 2 GB | |
llama3.2-vision | 11b | Jun/2025 | Meta AI | USA | 16 GB | 8 GB | 6 GB | |
llama3.2-vision | 90b | Jun/2025 | Meta AI | USA | 128 GB | 64 GB | 49 GB | |
llama3.3 | 70b | Sep/2024 | Meta AI | USA | 128 GB | 64 GB | 38 GB | |
llama4 | 16x17b | Dec/2024 | Meta AI | USA | 128 GB | 64 GB | 146 GB | |
llama4 | 128x17b | Dec/2024 | Meta AI | USA | 128 GB | 64 GB | 1166 GB | |
llama-guard3 | 1b | Jun/2024 | Meta AI | USA | 8 GB | 4 GB | 1 GB | |
llama-guard3 | 8b | Jun/2024 | Meta AI | USA | 16 GB | 8 GB | 4 GB | |
llava | 7b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 4 GB | |
llava | 13b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 7 GB | |
llava | 34b | Dec/2023 | LMSYS | USA | 64 GB | 32 GB | 18 GB | |
llava-llama3 | 8b | Jun/2024 | LMSYS | USA | 16 GB | 8 GB | 4 GB | |
llava-phi3 | 3.8b | Jun/2024 | LMSYS | USA | 8 GB | 4 GB | 2 GB | |
magicoder | 7b | Dec/2023 | Magicoder Team | China | 16 GB | 8 GB | 4 GB | |
marco-o1 | 7b | Dec/2023 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
mathstral | 7b | Jun/2024 | Mistral AI | France | 16 GB | 8 GB | 4 GB | |
meditron | 7b | Dec/2023 | EPFL LLMed | Switzerland | 16 GB | 8 GB | 4 GB | |
meditron | 70b | Dec/2023 | EPFL LLMed | Switzerland | 128 GB | 64 GB | 38 GB | |
medllama2 | 7b | Dec/2023 | | Unknown | 16 GB | 8 GB | 4 GB | |
megadolphin | 120b | Dec/2023 | Eric Hartford (Independent) | USA | 128 GB | 64 GB | 65 GB | |
minicpm-v | 8b | Jun/2025 | OpenBMB | China | 16 GB | 8 GB | 4 GB | |
mistral | 7b | Jun/2025 | Mistral AI | France | 16 GB | 8 GB | 4 GB | |
mistral-large | 123b | Jun/2024 | Mistral AI | France | 128 GB | 64 GB | 66 GB | |
mistral-nemo | 12b | Jun/2024 | Mistral AI | France | 16 GB | 8 GB | 6 GB | |
mistral-openorca | 7b | Dec/2023 | OpenOrca Team | USA | 16 GB | 8 GB | 4 GB | |
mistral-small | 22b | Jul/2024 | Mistral AI | France | 32 GB | 16 GB | 12 GB | |
mistral-small | 24b | Jul/2024 | Mistral AI | France | 32 GB | 16 GB | 13 GB | |
mistral-small3.1 | 24b | Mar/2025 | Mistral AI | France | 32 GB | 16 GB | 13 GB | |
mistrallite | 7b | Sep/2023 | Mistral AI | France | 16 GB | 8 GB | 4 GB | |
mixtral | 8x7b | Nov/2023 | Mistral AI | France | 64 GB | 32 GB | 4 GB | |
mixtral | 8x22b | Feb/2024 | Mistral AI | France | 128 GB | 64 GB | 12 GB | |
moondream | 1.8b | Dec/2023 | Vikhyat Khare (Independent) | USA | 8 GB | 4 GB | 1 GB | |
mxbai-embed-large | 335m | Dec/2023 | mixedbread.ai | Germany | 8 GB | 4 GB | 1 GB | |
nemotron | 70b | Jul/2024 | NVIDIA | USA | 128 GB | 64 GB | 38 GB | |
nemotron-mini | 4b | Jul/2024 | NVIDIA | USA | 8 GB | 4 GB | 2 GB | |
neural-chat | 7b | Dec/2023 | Intel | USA | 16 GB | 8 GB | 4 GB | |
nexusraven | 13b | Dec/2023 | Nexusflow | USA | 16 GB | 8 GB | 7 GB | |
nomic-embed-text | Unknown | Dec/2023 | Nomic AI | USA | 8 GB | 4 GB | 1 GB | |
notus | 7b | Dec/2023 | Argilla | Spain | 16 GB | 8 GB | 4 GB | |
notux | 8x7b | Dec/2023 | | Unknown | 64 GB | 32 GB | 4 GB | |
nous-hermes | 7b | Dec/2023 | Nous Research | USA | 16 GB | 8 GB | 4 GB | |
nous-hermes | 13b | Dec/2023 | Nous Research | USA | 16 GB | 8 GB | 7 GB | |
nous-hermes2 | 10.7b | Dec/2023 | Nous Research | USA | 16 GB | 8 GB | 6 GB | |
nous-hermes2 | 34b | Dec/2023 | Nous Research | USA | 64 GB | 32 GB | 18 GB | |
nous-hermes2-mixtral | 8x7b | Jul/2024 | Nous Research | USA | 64 GB | 32 GB | 4 GB | |
nuextract | 3.8b | Jun/2024 | | Unknown | 8 GB | 4 GB | 2 GB | |
olmo2 | 7b | Mar/2024 | The Allen Institute for AI | USA | 16 GB | 8 GB | 4 GB | |
olmo2 | 13b | Mar/2024 | The Allen Institute for AI | USA | 16 GB | 8 GB | 7 GB | |
opencoder | 1.5b | Dec/2023 | INF and M-A-P | Unknown | 8 GB | 4 GB | 1 GB | |
opencoder | 8b | Dec/2023 | INF and M-A-P | Unknown | 16 GB | 8 GB | 4 GB | |
openchat | 7b | Dec/2023 | OpenChat Team | China | 16 GB | 8 GB | 4 GB | |
openhermes | 7b | Dec/2023 | Teknium | USA | 16 GB | 8 GB | 4 GB | |
openthinker | 7b | Apr/2025 | | Unknown | 16 GB | 8 GB | 4 GB | |
openthinker | 32b | Apr/2025 | | Unknown | 64 GB | 32 GB | 17 GB | |
open-orca-platypus2 | 13b | Dec/2023 | OpenOrca Team | USA | 16 GB | 8 GB | 7 GB | |
orca-mini | 3b | Dec/2023 | LMSYS | USA | 8 GB | 4 GB | 2 GB | |
orca-mini | 7b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 4 GB | |
orca-mini | 13b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 7 GB | |
orca-mini | 70b | Dec/2023 | LMSYS | USA | 128 GB | 64 GB | 38 GB | |
orca2 | 7b | Dec/2023 | Microsoft | USA | 16 GB | 8 GB | 4 GB | |
orca2 | 13b | Dec/2023 | Microsoft | USA | 16 GB | 8 GB | 7 GB | |
paraphrase-multilingual | 278m | Dec/2023 | Helsinki-NLP | Finland | 8 GB | 4 GB | 1 GB | |
phi | 2.7b | Nov/2023 | Microsoft | USA | 8 GB | 4 GB | 1 GB | |
phi3 | 3.8b | Mar/2024 | Microsoft | USA | 8 GB | 4 GB | 2 GB | |
phi3.5 | 3.8b | Jul/2024 | Microsoft | USA | 8 GB | 4 GB | 2 GB | |
phi4 | 14b | Sep/2024 | Microsoft | USA | 16 GB | 8 GB | 8 GB | |
phi4-mini | 3.8b | Sep/2024 | Microsoft | USA | 8 GB | 4 GB | 2 GB | |
phi4-mini-reasoning | 3.8b | Mar/2025 | Microsoft | USA | 8 GB | 4 GB | 2 GB | |
phi4-reasoning | 14b | Mar/2025 | Microsoft | USA | 16 GB | 8 GB | 8 GB | |
phind-codellama | 34b | Dec/2023 | Phind | USA | 64 GB | 32 GB | 18 GB | |
qwen | 0.5b | Oct/2023 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen | 1.8b | Oct/2023 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen | 4b | Oct/2023 | Alibaba Cloud | China | 8 GB | 4 GB | 2 GB | |
qwen | 7b | Oct/2023 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen | 14b | Oct/2023 | Alibaba Cloud | China | 16 GB | 8 GB | 8 GB | |
qwen | 32b | Oct/2023 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
qwen | 72b | Oct/2023 | Alibaba Cloud | China | 128 GB | 64 GB | 39 GB | |
qwen | 110b | Oct/2023 | Alibaba Cloud | China | 128 GB | 64 GB | 59 GB | |
qwen2 | 0.5b | May/2024 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2 | 1.5b | May/2024 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2 | 7b | May/2024 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen2 | 72b | May/2024 | Alibaba Cloud | China | 128 GB | 64 GB | 39 GB | |
qwen2.5 | 0.5b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2.5 | 1.5b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2.5 | 3b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 2 GB | |
qwen2.5 | 7b | Jun/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen2.5 | 14b | Jun/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 8 GB | |
qwen2.5 | 32b | Jun/2025 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
qwen2.5 | 72b | Jun/2025 | Alibaba Cloud | China | 128 GB | 64 GB | 39 GB | |
qwen2.5-coder | 0.5b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2.5-coder | 1.5b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2.5-coder | 3b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 2 GB | |
qwen2.5-coder | 7b | Jun/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen2.5-coder | 14b | Jun/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 8 GB | |
qwen2.5-coder | 32b | Jun/2025 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
qwen2.5vl | 3b | Jun/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 2 GB | |
qwen2.5vl | 7b | Jun/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen2.5vl | 32b | Jun/2025 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
qwen2.5vl | 72b | Jun/2025 | Alibaba Cloud | China | 128 GB | 64 GB | 39 GB | |
qwen2-math | 1.5b | Jul/2024 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen2-math | 7b | Jul/2024 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen2-math | 72b | Jul/2024 | Alibaba Cloud | China | 128 GB | 64 GB | 39 GB | |
qwen3 | 0.6b | Mar/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen3 | 1.7b | Mar/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 1 GB | |
qwen3 | 4b | Mar/2025 | Alibaba Cloud | China | 8 GB | 4 GB | 2 GB | |
qwen3 | 8b | Mar/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 4 GB | |
qwen3 | 14b | Mar/2025 | Alibaba Cloud | China | 16 GB | 8 GB | 8 GB | |
qwen3 | 30b | Mar/2025 | Alibaba Cloud | China | 32 GB | 16 GB | 16 GB | |
qwen3 | 32b | Mar/2025 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
qwen3 | 235b | Mar/2025 | Alibaba Cloud | China | 128 GB | 64 GB | 127 GB | |
qwq | 32b | Jun/2025 | Alibaba Cloud | China | 64 GB | 32 GB | 17 GB | |
r1-1776 | 70b | Mar/2024 | Perplexity | USA | 128 GB | 64 GB | 38 GB | |
r1-1776 | 671b | Mar/2024 | Perplexity | USA | 128 GB | 64 GB | 362 GB | |
reader-lm | 0.5b | Jul/2024 | Jina AI | Germany | 8 GB | 4 GB | 1 GB | |
reader-lm | 1.5b | Jul/2024 | Jina AI | Germany | 8 GB | 4 GB | 1 GB | |
reflection | 70b | Jul/2024 | xAI | USA | 128 GB | 64 GB | 38 GB | |
sailor2 | 1b | Dec/2023 | | Unknown | 8 GB | 4 GB | 1 GB | |
sailor2 | 8b | Dec/2023 | | Unknown | 16 GB | 8 GB | 4 GB | |
sailor2 | 20b | Dec/2023 | | Unknown | 32 GB | 16 GB | 11 GB | |
samantha-mistral | 7b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
shieldgemma | 2b | Jun/2024 | Google DeepMind | UK | 8 GB | 4 GB | 1 GB | |
shieldgemma | 9b | Jun/2024 | Google DeepMind | UK | 16 GB | 8 GB | 5 GB | |
shieldgemma | 27b | Jun/2024 | Google DeepMind | UK | 32 GB | 16 GB | 15 GB | |
smallthinker | 3b | Jul/2024 | | Unknown | 8 GB | 4 GB | 2 GB | |
smollm | 135m | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
smollm | 360m | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
smollm | 1.7b | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
smollm2 | 135m | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
smollm2 | 360m | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
smollm2 | 1.7b | Jun/2024 | Hugging Face | USA/France | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed | 22m | Mar/2024 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed | 33m | Mar/2024 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed | 110m | Mar/2024 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed | 137m | Mar/2024 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed | 335m | Mar/2024 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
snowflake-arctic-embed2 | 568m | Dec/2023 | Snowflake | USA | 8 GB | 4 GB | 1 GB | |
solar | 10.7b | Dec/2023 | Upstage AI | South Korea | 16 GB | 8 GB | 6 GB | |
solar-pro | 22b | Jul/2024 | | Unknown | 32 GB | 16 GB | 12 GB | |
stable-beluga | 7b | Dec/2023 | Stability AI | UK | 16 GB | 8 GB | 4 GB | |
stable-beluga | 13b | Dec/2023 | Stability AI | UK | 16 GB | 8 GB | 7 GB | |
stable-beluga | 70b | Dec/2023 | Stability AI | UK | 128 GB | 64 GB | 38 GB | |
stable-code | 3b | Dec/2023 | Stability AI | UK | 8 GB | 4 GB | 2 GB | |
stablelm-zephyr | 3b | Dec/2023 | Stability AI | UK | 8 GB | 4 GB | 2 GB | |
stablelm2 | 1.6b | Dec/2023 | Stability AI | UK | 8 GB | 4 GB | 1 GB | |
stablelm2 | 12b | Dec/2023 | Stability AI | UK | 16 GB | 8 GB | 6 GB | |
starcoder | 1b | Apr/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 8 GB | 4 GB | 1 GB | |
starcoder | 3b | Apr/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 8 GB | 4 GB | 2 GB | |
starcoder | 7b | Apr/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 16 GB | 8 GB | 4 GB | |
starcoder | 15b | Apr/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 16 GB | 8 GB | 8 GB | |
starcoder2 | 3b | Dec/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 8 GB | 4 GB | 2 GB | |
starcoder2 | 7b | Dec/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 16 GB | 8 GB | 4 GB | |
starcoder2 | 15b | Dec/2023 | BigCode (Hugging Face/ServiceNow) | USA/France | 16 GB | 8 GB | 8 GB | |
starling-lm | 7b | Dec/2023 | Berkeley NEST | USA | 16 GB | 8 GB | 4 GB | |
tinydolphin | 1.1b | Dec/2023 | Eric Hartford (Independent) | USA | 8 GB | 4 GB | 1 GB | |
tinyllama | 1.1b | Dec/2023 | TinyLlama Project | China | 8 GB | 4 GB | 1 GB | |
tulu3 | 8b | Jul/2024 | The Allen Institute for AI | USA | 16 GB | 8 GB | 4 GB | |
tulu3 | 70b | Jul/2024 | The Allen Institute for AI | USA | 128 GB | 64 GB | 38 GB | |
vicuna | 7b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 4 GB | |
vicuna | 13b | Dec/2023 | LMSYS | USA | 16 GB | 8 GB | 7 GB | |
vicuna | 33b | Dec/2023 | LMSYS | USA | 64 GB | 32 GB | 18 GB | |
wizard-math | 7b | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 16 GB | 8 GB | 4 GB | |
wizard-math | 13b | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 16 GB | 8 GB | 7 GB | |
wizard-math | 70b | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 128 GB | 64 GB | 38 GB | |
wizard-vicuna | 13b | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 16 GB | 8 GB | 7 GB | |
wizard-vicuna-uncensored | 7b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 4 GB | |
wizard-vicuna-uncensored | 13b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 7 GB | |
wizard-vicuna-uncensored | 30b | Dec/2023 | Eric Hartford (Independent) | USA | 32 GB | 16 GB | 16 GB | |
wizardcoder | 33b | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 64 GB | 32 GB | 18 GB | |
wizardlm | Unknown | Dec/2023 | WizardLM Team (Microsoft Research) | USA | 8 GB | 4 GB | 1 GB | |
wizardlm-uncensored | 13b | Dec/2023 | Eric Hartford (Independent) | USA | 16 GB | 8 GB | 7 GB | |
wizardlm2 | 7b | Mar/2024 | Microsoft | USA | 16 GB | 8 GB | 4 GB | |
wizardlm2 | 8x22b | Mar/2024 | Microsoft | USA | 128 GB | 64 GB | 12 GB | |
xwinlm | 7b | Dec/2023 | Xwin-LM Team | China | 16 GB | 8 GB | 4 GB | |
xwinlm | 13b | Dec/2023 | Xwin-LM Team | China | 16 GB | 8 GB | 7 GB | |
yarn-llama2 | 7b | Dec/2023 | Maxime Labonne (Independent) | France | 16 GB | 8 GB | 4 GB | |
yarn-llama2 | 13b | Dec/2023 | Maxime Labonne (Independent) | France | 16 GB | 8 GB | 7 GB | |
yarn-mistral | 7b | Dec/2023 | Maxime Labonne (Independent) | France | 16 GB | GB | 4 GB | |