Model Variant Release date Company Country RAM needed VRAM needed Diskspace Use cases
all-minilm22mDec/2023 Sentence Transformers Germany8 GB 4 GB 1 GB Natural Language Understanding,Data Analysis
all-minilm33mDec/2023 Sentence Transformers Germany8 GB 4 GB 1 GB Natural Language Understanding,Data Analysis
alfred40bDec/2023Unknown64 GB 32 GB 22 GB Text Generation,Natural Language Understanding
athene-v272bNov/2024Unknown128 GB 64 GB 39 GB Text Generation,Natural Language Understanding
aya8bJan/2024 Cohere Canada16 GB 8 GB 4 GB Text Generation,Natural Language Understanding,Machine Translation
aya35bJan/2024 Cohere Canada64 GB 32 GB 19 GB Text Generation,Natural Language Understanding,Machine Translation
aya-expanse8bJun/2024 Cohere Canada16 GB 8 GB 4 GB Text Generation,Natural Language Understanding,Machine Translation
aya-expanse32bJun/2024 Cohere Canada64 GB 32 GB 17 GB Text Generation,Natural Language Understanding,Machine Translation
bakllava7bDec/2023 Skunkworks AI USA16 GB 8 GB 4 GB Image Classification,Natural Language Understanding
bespoke-minicheck7bJul/2024 Bespoke Labs USA16 GB 8 GB 4 GB
bge-large335mJan/2024 BAAI China8 GB 4 GB 1 GB
bge-m3567mJan/2024 BAAI China8 GB 4 GB 1 GB
codebooga34bDec/2023 TheBloke (Independent) UK64 GB 32 GB 18 GB
codegemma2bMar/2024 Google DeepMind UK8 GB 4 GB 1 GB
codegemma7bMar/2024 Google DeepMind UK16 GB 8 GB 4 GB
codeqwen7bOct/2023 Alibaba Cloud China16 GB 8 GB 4 GB
codeqeex49bJun/2024 xAI USA16 GB 8 GB 5 GB
codellama7bJul/2023 Meta AI USA16 GB 8 GB 4 GB
codellama13bJul/2023 Meta AI USA16 GB 8 GB 7 GB
codellama34bJul/2023 Meta AI USA64 GB 32 GB 18 GB
codellama70bJul/2023 Meta AI USA128 GB 64 GB 38 GB
codestral22bApr/2024 Mistral AI France32 GB 16 GB 12 GB
codeup13bDec/2023 DeepSEUnknown16 GB 8 GB 7 GB
cogito3bNov/2024 Deep Cogito USA8 GB 4 GB 2 GB
cogito8bNov/2024 Deep Cogito USA16 GB 8 GB 4 GB
cogito14bNov/2024 Deep Cogito USA16 GB 8 GB 8 GB
cogito32bNov/2024 Deep Cogito USA64 GB 32 GB 17 GB
cogito70bNov/2024 Deep Cogito USA128 GB 64 GB 38 GB
command-a111bFeb/2025 Cohere Canada128 GB 64 GB 60 GB
command-r35bFeb/2024 Cohere Canada64 GB 32 GB 19 GB
command-r-plus104bMar/2024 Cohere Canada128 GB 64 GB 56 GB
command-r7b7bFeb/2025 Cohere Canada16 GB 8 GB 4 GB
command-r7b-arabic7bFeb/2025 Cohere Canada16 GB 8 GB 4 GB
dbrx132bFeb/2024 Databricks USA128 GB 64 GB 71 GB
deepcoder1.5bNov/2024Unknown8 GB 4 GB 1 GB
deepcoder14bNov/2024Unknown16 GB 8 GB 8 GB
deepseek-coder1.3bDec/2023 DeepSeek China8 GB 4 GB 1 GB
deepseek-coder6.7bDec/2023 DeepSeek China16 GB 8 GB 4 GB
deepseek-coder33bDec/2023 DeepSeek China64 GB 32 GB 18 GB
deepseek-coder-v216bMay/2024 DeepSeek China32 GB 16 GB 9 GB
deepseek-coder-v2236bMay/2024 DeepSeek China128 GB 64 GB 127 GB
deepseek-llm7bDec/2023 DeepSeek China16 GB 8 GB 4 GB
deepseek-llm67bDec/2023 DeepSeek China128 GB 64 GB 36 GB
deepseek-r11.5bApr/2025 DeepSeek China8 GB 4 GB 1 GB
deepseek-r17bApr/2025 DeepSeek China16 GB 8 GB 4 GB
deepseek-r18bApr/2025 DeepSeek China16 GB 8 GB 4 GB
deepseek-r114bApr/2025 DeepSeek China16 GB 8 GB 8 GB
deepseek-r132bApr/2025 DeepSeek China64 GB 32 GB 17 GB
deepseek-r170bApr/2025 DeepSeek China128 GB 64 GB 38 GB
deepseek-r1671bApr/2025 DeepSeek China128 GB 64 GB 362 GB
deepseek-v216bApr/2024 DeepSeek China32 GB 16 GB 9 GB
deepseek-v2.5236bJul/2024 DeepSeek China128 GB 64 GB 127 GB
deepseek-v3671bOct/2024 DeepSeek China128 GB 64 GB 362 GB
deepscaler1.5bFeb/2025 DeepSeek China8 GB 4 GB 1 GB
devstral24bApr/2025 xAI USA32 GB 16 GB 13 GB
dolphin-llama38bMar/2024 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
dolphin-llama370bMar/2024 Eric Hartford (Independent) USA128 GB 64 GB 38 GB
dolphin-mistral7bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
dolphin-mixtral8x7bMar/2024 Eric Hartford (Independent) USA64 GB 32 GB 4 GB
dolphin-mixtral8x22bMar/2024 Eric Hartford (Independent) USA128 GB 64 GB 12 GB
dolphin-phi2.7bDec/2023 Microsoft USA8 GB 4 GB 1 GB
dolphin38bMar/2024 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
dolphincoder7bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
dolphincoder15bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 8 GB
duckdb-nsql7bDec/2023 MotherDuck USA16 GB 8 GB 4 GB
everythinglm13bDec/2023Unknown16 GB 8 GB 7 GB
exaone3.52.4bJan/2024 LG AI Research South Korea8 GB 4 GB 1 GB
exaone3.57.8bJan/2024 LG AI Research South Korea16 GB 8 GB 4 GB
exaone3.532bJan/2024 LG AI Research South Korea64 GB 32 GB 17 GB
exaone-deep2.4bMar/2025 LG AI Research South Korea8 GB 4 GB 1 GB
exaone-deep7.8bMar/2025 LG AI Research South Korea16 GB 8 GB 4 GB
exaone-deep32bMar/2025 LG AI Research South Korea64 GB 32 GB 17 GB
falcon7bFeb/2023 Technology Innovation Institute UAE16 GB 8 GB 4 GB
falcon40bFeb/2023 Technology Innovation Institute UAE64 GB 32 GB 22 GB
falcon180bFeb/2023 Technology Innovation Institute UAE128 GB 64 GB 97 GB
falcon211bApr/2024 Technology Innovation Institute UAE16 GB 8 GB 6 GB
falcon31bFeb/2024 Technology Innovation Institute UAE8 GB 4 GB 1 GB
falcon33bFeb/2024 Technology Innovation Institute UAE8 GB 4 GB 2 GB
falcon37bFeb/2024 Technology Innovation Institute UAE16 GB 8 GB 4 GB
falcon310bFeb/2024 Technology Innovation Institute UAE16 GB 8 GB 5 GB
firefunction-v270bJul/2024Unknown128 GB 64 GB 38 GB
gemma2bJan/2024 Google DeepMind UK8 GB 4 GB 1 GB
gemma7bJan/2024 Google DeepMind UK16 GB 8 GB 4 GB
gemma22bMay/2024 Google DeepMind UK8 GB 4 GB 1 GB
gemma29bMay/2024 Google DeepMind UK16 GB 8 GB 5 GB
gemma227bMay/2024 Google DeepMind UK32 GB 16 GB 15 GB
gemma31bMar/2025 Google DeepMind UK8 GB 4 GB 1 GB
gemma34bMar/2025 Google DeepMind UK8 GB 4 GB 2 GB
gemma312bMar/2025 Google DeepMind UK16 GB 8 GB 6 GB
gemma327bMar/2025 Google DeepMind UK32 GB 16 GB 15 GB
glm49bJun/2024 Tsinghua KEG China16 GB 8 GB 5 GB
goliath120bDec/2023Unknown128 GB 64 GB 65 GB
granite-code3bApr/2024 IBM USA8 GB 4 GB 2 GB
granite-code8bApr/2024 IBM USA16 GB 8 GB 4 GB
granite-code20bApr/2024 IBM USA32 GB 16 GB 11 GB
granite-code34bApr/2024 IBM USA64 GB 32 GB 18 GB
granite-embedding30mFeb/2024 IBM USA8 GB 4 GB 1 GB
granite-embedding278mFeb/2024 IBM USA8 GB 4 GB 1 GB
granite3-dense2bDec/2023 IBM USA8 GB 4 GB 1 GB
granite3-dense8bDec/2023 IBM USA16 GB 8 GB 4 GB
granite3-moe1bDec/2023 IBM USA8 GB 4 GB 1 GB
granite3-moe3bDec/2023 IBM USA8 GB 4 GB 2 GB
granite3.1-dense2bFeb/2024 IBM USA8 GB 4 GB 1 GB
granite3.1-dense8bFeb/2024 IBM USA16 GB 8 GB 4 GB
granite3.1-moe1bFeb/2024 IBM USA8 GB 4 GB 1 GB
granite3.1-moe3bFeb/2024 IBM USA8 GB 4 GB 2 GB
granite3.22bMar/2024 IBM USA8 GB 4 GB 1 GB
granite3.28bMar/2024 IBM USA16 GB 8 GB 4 GB
granite3.2-vision2bMar/2024 IBM USA8 GB 4 GB 1 GB
granite3.32bMar/2025 IBM USA8 GB 4 GB 1 GB
granite3.38bMar/2025 IBM USA16 GB 8 GB 4 GB
granite3-guardian2bDec/2023 IBM USA8 GB 4 GB 1 GB
granite3-guardian8bDec/2023 IBM USA16 GB 8 GB 4 GB
hermes33bJul/2024 Nous Research USA8 GB 4 GB 2 GB
hermes38bJul/2024 Nous Research USA16 GB 8 GB 4 GB
hermes370bJul/2024 Nous Research USA128 GB 64 GB 38 GB
hermes3405bJul/2024 Nous Research USA128 GB 64 GB 219 GB
internlm21mJun/2024 Shanghai AI Laboratory China8 GB 4 GB 1 GB
internlm21.8bJun/2024 Shanghai AI Laboratory China8 GB 4 GB 1 GB
internlm27bJun/2024 Shanghai AI Laboratory China16 GB 8 GB 4 GB
internlm220bJun/2024 Shanghai AI Laboratory China32 GB 16 GB 11 GB
llama-proUnknownDec/2023Unknown8 GB 4 GB 1 GB
llama27bJun/2023 Meta AI USA16 GB 8 GB 4 GB
llama213bJun/2023 Meta AI USA16 GB 8 GB 7 GB
llama270bJun/2023 Meta AI USA128 GB 64 GB 38 GB
llama2-chinese7bJun/2023 Chinese-LLaMA-Alpaca Team China16 GB 8 GB 4 GB
llama2-chinese13bJun/2023 Chinese-LLaMA-Alpaca Team China16 GB 8 GB 7 GB
llama2-uncensored7bJul/2023 George Sung (Independent) USA16 GB 8 GB 4 GB
llama2-uncensored70bJul/2023 George Sung (Independent) USA128 GB 64 GB 38 GB
llama38bMar/2024 Meta AI USA16 GB 8 GB 4 GB
llama370bMar/2024 Meta AI USA128 GB 64 GB 38 GB
llama3-chatqa8bJun/2024 NVIDIA USA16 GB 8 GB 4 GB
llama3-chatqa70bJun/2024 NVIDIA USA128 GB 64 GB 38 GB
llama3-gradient8bMay/2024 USA16 GB 8 GB 4 GB
llama3-gradient70bMay/2024 USA128 GB 64 GB 38 GB
llama3-groq-tool-use8bJul/2024 Groq USA16 GB 8 GB 4 GB
llama3-groq-tool-use70bJul/2024 Groq USA128 GB 64 GB 38 GB
llama3.18bJun/2024 Meta AI USA16 GB 8 GB 4 GB
llama3.170bJun/2024 Meta AI USA128 GB 64 GB 38 GB
llama3.1405bJun/2024 Meta AI USA128 GB 64 GB 219 GB
llama3.21bJun/2025 Meta AI USA8 GB 4 GB 1 GB
llama3.23bJun/2025 Meta AI USA8 GB 4 GB 2 GB
llama3.2-vision11bJun/2025 Meta AI USA16 GB 8 GB 6 GB
llama3.2-vision90bJun/2025 Meta AI USA128 GB 64 GB 49 GB
llama3.370bSep/2024 Meta AI USA128 GB 64 GB 38 GB
llama416x17bDec/2024 Meta AI USA128 GB 64 GB 146 GB
llama4128x17bDec/2024 Meta AI USA128 GB 64 GB 1166 GB
llama-guard31bJun/2024 Meta AI USA8 GB 4 GB 1 GB
llama-guard38bJun/2024 Meta AI USA16 GB 8 GB 4 GB
llava7bDec/2023 LMSYS USA16 GB 8 GB 4 GB
llava13bDec/2023 LMSYS USA16 GB 8 GB 7 GB
llava34bDec/2023 LMSYS USA64 GB 32 GB 18 GB
llava-llama38bJun/2024 LMSYS USA16 GB 8 GB 4 GB
llava-phi33.8bJun/2024 LMSYS USA8 GB 4 GB 2 GB
magicoder7bDec/2023 Magicoder Team China16 GB 8 GB 4 GB
marco-o17bDec/2023 Alibaba Cloud China16 GB 8 GB 4 GB
mathstral7bJun/2024 Mistral AI France16 GB 8 GB 4 GB
meditron7bDec/2023 EPFL LLMed Switzerland16 GB 8 GB 4 GB
meditron70bDec/2023 EPFL LLMed Switzerland128 GB 64 GB 38 GB
medllama27bDec/2023Unknown16 GB 8 GB 4 GB
megadolphin120bDec/2023 Eric Hartford (Independent) USA128 GB 64 GB 65 GB
minicpm-v8bJun/2025 OpenBMB China16 GB 8 GB 4 GB
mistral7bJun/2025 Mistral AI France16 GB 8 GB 4 GB
mistral-large123bJun/2024 Mistral AI France128 GB 64 GB 66 GB
mistral-nemo12bJun/2024 Mistral AI France16 GB 8 GB 6 GB
mistral-openorca7bDec/2023 OpenOrca Team USA16 GB 8 GB 4 GB
mistral-small22bJul/2024 Mistral AI France32 GB 16 GB 12 GB
mistral-small24bJul/2024 Mistral AI France32 GB 16 GB 13 GB
mistral-small3.124bMar/2025 Mistral AI France32 GB 16 GB 13 GB
mistrallite7bSep/2023 Mistral AI France16 GB 8 GB 4 GB
mixtral8x7bNov/2023 Mistral AI France64 GB 32 GB 4 GB
mixtral8x22bFeb/2024 Mistral AI France128 GB 64 GB 12 GB
moondream1.8bDec/2023 Vikhyat Khare (Independent) USA8 GB 4 GB 1 GB
mxbai-embed-large335mDec/2023 mixedbread.ai Germany8 GB 4 GB 1 GB
nemotron70bJul/2024 NVIDIA USA128 GB 64 GB 38 GB
nemotron-mini4bJul/2024 NVIDIA USA8 GB 4 GB 2 GB
neural-chat7bDec/2023 Intel USA16 GB 8 GB 4 GB
nexusraven13bDec/2023 Nexusflow USA16 GB 8 GB 7 GB
nomic-embed-textUnknownDec/2023 Nomic AI USA8 GB 4 GB 1 GB
notus7bDec/2023 Argilla Spain16 GB 8 GB 4 GB
notux8x7bDec/2023Unknown64 GB 32 GB 4 GB
nous-hermes7bDec/2023 Nous Research USA16 GB 8 GB 4 GB
nous-hermes13bDec/2023 Nous Research USA16 GB 8 GB 7 GB
nous-hermes210.7bDec/2023 Nous Research USA16 GB 8 GB 6 GB
nous-hermes234bDec/2023 Nous Research USA64 GB 32 GB 18 GB
nous-hermes2-mixtral8x7bJul/2024 Nous Research USA64 GB 32 GB 4 GB
nuextract3.8bJun/2024Unknown8 GB 4 GB 2 GB
olmo27bMar/2024 The Allen Institute for AI USA16 GB 8 GB 4 GB
olmo213bMar/2024 The Allen Institute for AI USA16 GB 8 GB 7 GB
opencoder1.5bDec/2023 INF and M-A-PUnknown8 GB 4 GB 1 GB
opencoder8bDec/2023 INF and M-A-PUnknown16 GB 8 GB 4 GB
openchat7bDec/2023 OpenChat Team China16 GB 8 GB 4 GB
openhermes7bDec/2023 Teknium USA16 GB 8 GB 4 GB
openthinker7bApr/2025Unknown16 GB 8 GB 4 GB
openthinker32bApr/2025Unknown64 GB 32 GB 17 GB
open-orca-platypus213bDec/2023 OpenOrca Team USA16 GB 8 GB 7 GB
orca-mini3bDec/2023 LMSYS USA8 GB 4 GB 2 GB
orca-mini7bDec/2023 LMSYS USA16 GB 8 GB 4 GB
orca-mini13bDec/2023 LMSYS USA16 GB 8 GB 7 GB
orca-mini70bDec/2023 LMSYS USA128 GB 64 GB 38 GB
orca27bDec/2023 Microsoft USA16 GB 8 GB 4 GB
orca213bDec/2023 Microsoft USA16 GB 8 GB 7 GB
paraphrase-multilingual278mDec/2023 Helsinki-NLP Finland8 GB 4 GB 1 GB
phi2.7bNov/2023 Microsoft USA8 GB 4 GB 1 GB
phi33.8bMar/2024 Microsoft USA8 GB 4 GB 2 GB
phi3.53.8bJul/2024 Microsoft USA8 GB 4 GB 2 GB
phi414bSep/2024 Microsoft USA16 GB 8 GB 8 GB
phi4-mini3.8bSep/2024 Microsoft USA8 GB 4 GB 2 GB
phi4-mini-reasoning3.8bMar/2025 Microsoft USA8 GB 4 GB 2 GB
phi4-reasoning14bMar/2025 Microsoft USA16 GB 8 GB 8 GB
phind-codellama34bDec/2023 Phind USA64 GB 32 GB 18 GB
qwen0.5bOct/2023 Alibaba Cloud China8 GB 4 GB 1 GB
qwen1.8bOct/2023 Alibaba Cloud China8 GB 4 GB 1 GB
qwen4bOct/2023 Alibaba Cloud China8 GB 4 GB 2 GB
qwen7bOct/2023 Alibaba Cloud China16 GB 8 GB 4 GB
qwen14bOct/2023 Alibaba Cloud China16 GB 8 GB 8 GB
qwen32bOct/2023 Alibaba Cloud China64 GB 32 GB 17 GB
qwen72bOct/2023 Alibaba Cloud China128 GB 64 GB 39 GB
qwen110bOct/2023 Alibaba Cloud China128 GB 64 GB 59 GB
qwen20.5bMay/2024 Alibaba Cloud China8 GB 4 GB 1 GB
qwen21.5bMay/2024 Alibaba Cloud China8 GB 4 GB 1 GB
qwen27bMay/2024 Alibaba Cloud China16 GB 8 GB 4 GB
qwen272bMay/2024 Alibaba Cloud China128 GB 64 GB 39 GB
qwen2.50.5bJun/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen2.51.5bJun/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen2.53bJun/2025 Alibaba Cloud China8 GB 4 GB 2 GB
qwen2.57bJun/2025 Alibaba Cloud China16 GB 8 GB 4 GB
qwen2.514bJun/2025 Alibaba Cloud China16 GB 8 GB 8 GB
qwen2.532bJun/2025 Alibaba Cloud China64 GB 32 GB 17 GB
qwen2.572bJun/2025 Alibaba Cloud China128 GB 64 GB 39 GB
qwen2.5-coder0.5bJun/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen2.5-coder1.5bJun/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen2.5-coder3bJun/2025 Alibaba Cloud China8 GB 4 GB 2 GB
qwen2.5-coder7bJun/2025 Alibaba Cloud China16 GB 8 GB 4 GB
qwen2.5-coder14bJun/2025 Alibaba Cloud China16 GB 8 GB 8 GB
qwen2.5-coder32bJun/2025 Alibaba Cloud China64 GB 32 GB 17 GB
qwen2.5vl3bJun/2025 Alibaba Cloud China8 GB 4 GB 2 GB
qwen2.5vl7bJun/2025 Alibaba Cloud China16 GB 8 GB 4 GB
qwen2.5vl32bJun/2025 Alibaba Cloud China64 GB 32 GB 17 GB
qwen2.5vl72bJun/2025 Alibaba Cloud China128 GB 64 GB 39 GB
qwen2-math1.5bJul/2024 Alibaba Cloud China8 GB 4 GB 1 GB
qwen2-math7bJul/2024 Alibaba Cloud China16 GB 8 GB 4 GB
qwen2-math72bJul/2024 Alibaba Cloud China128 GB 64 GB 39 GB
qwen30.6bMar/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen31.7bMar/2025 Alibaba Cloud China8 GB 4 GB 1 GB
qwen34bMar/2025 Alibaba Cloud China8 GB 4 GB 2 GB
qwen38bMar/2025 Alibaba Cloud China16 GB 8 GB 4 GB
qwen314bMar/2025 Alibaba Cloud China16 GB 8 GB 8 GB
qwen330bMar/2025 Alibaba Cloud China32 GB 16 GB 16 GB
qwen332bMar/2025 Alibaba Cloud China64 GB 32 GB 17 GB
qwen3235bMar/2025 Alibaba Cloud China128 GB 64 GB 127 GB
qwq32bJun/2025 Alibaba Cloud China64 GB 32 GB 17 GB
r1-177670bMar/2024 Perplexity USA128 GB 64 GB 38 GB
r1-1776671bMar/2024 Perplexity USA128 GB 64 GB 362 GB
reader-lm0.5bJul/2024 Jina AI Germany8 GB 4 GB 1 GB
reader-lm1.5bJul/2024 Jina AI Germany8 GB 4 GB 1 GB
reflection70bJul/2024 xAI USA128 GB 64 GB 38 GB
sailor21bDec/2023Unknown8 GB 4 GB 1 GB
sailor28bDec/2023Unknown16 GB 8 GB 4 GB
sailor220bDec/2023Unknown32 GB 16 GB 11 GB
samantha-mistral7bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
shieldgemma2bJun/2024 Google DeepMind UK8 GB 4 GB 1 GB
shieldgemma9bJun/2024 Google DeepMind UK16 GB 8 GB 5 GB
shieldgemma27bJun/2024 Google DeepMind UK32 GB 16 GB 15 GB
smallthinker3bJul/2024Unknown8 GB 4 GB 2 GB
smollm135mJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
smollm360mJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
smollm1.7bJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
smollm2135mJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
smollm2360mJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
smollm21.7bJun/2024 Hugging FaceUSA/France8 GB 4 GB 1 GB
snowflake-arctic-embed22mMar/2024 Snowflake USA8 GB 4 GB 1 GB
snowflake-arctic-embed33mMar/2024 Snowflake USA8 GB 4 GB 1 GB
snowflake-arctic-embed110mMar/2024 Snowflake USA8 GB 4 GB 1 GB
snowflake-arctic-embed137mMar/2024 Snowflake USA8 GB 4 GB 1 GB
snowflake-arctic-embed335mMar/2024 Snowflake USA8 GB 4 GB 1 GB
snowflake-arctic-embed2568mDec/2023 Snowflake USA8 GB 4 GB 1 GB
solar10.7bDec/2023 Upstage AI South Korea16 GB 8 GB 6 GB
solar-pro22bJul/2024Unknown32 GB 16 GB 12 GB
stable-beluga7bDec/2023 Stability AI UK16 GB 8 GB 4 GB
stable-beluga13bDec/2023 Stability AI UK16 GB 8 GB 7 GB
stable-beluga70bDec/2023 Stability AI UK128 GB 64 GB 38 GB
stable-code3bDec/2023 Stability AI UK8 GB 4 GB 2 GB
stablelm-zephyr3bDec/2023 Stability AI UK8 GB 4 GB 2 GB
stablelm21.6bDec/2023 Stability AI UK8 GB 4 GB 1 GB
stablelm212bDec/2023 Stability AI UK16 GB 8 GB 6 GB
starcoder1bApr/2023 BigCode (Hugging Face/ServiceNow)USA/France8 GB 4 GB 1 GB
starcoder3bApr/2023 BigCode (Hugging Face/ServiceNow)USA/France8 GB 4 GB 2 GB
starcoder7bApr/2023 BigCode (Hugging Face/ServiceNow)USA/France16 GB 8 GB 4 GB
starcoder15bApr/2023 BigCode (Hugging Face/ServiceNow)USA/France16 GB 8 GB 8 GB
starcoder23bDec/2023 BigCode (Hugging Face/ServiceNow)USA/France8 GB 4 GB 2 GB
starcoder27bDec/2023 BigCode (Hugging Face/ServiceNow)USA/France16 GB 8 GB 4 GB
starcoder215bDec/2023 BigCode (Hugging Face/ServiceNow)USA/France16 GB 8 GB 8 GB
starling-lm7bDec/2023 Berkeley NEST USA16 GB 8 GB 4 GB
tinydolphin1.1bDec/2023 Eric Hartford (Independent) USA8 GB 4 GB 1 GB
tinyllama1.1bDec/2023 TinyLlama Project China8 GB 4 GB 1 GB
tulu38bJul/2024 The Allen Institute for AI USA16 GB 8 GB 4 GB
tulu370bJul/2024 The Allen Institute for AI USA128 GB 64 GB 38 GB
vicuna7bDec/2023 LMSYS USA16 GB 8 GB 4 GB
vicuna13bDec/2023 LMSYS USA16 GB 8 GB 7 GB
vicuna33bDec/2023 LMSYS USA64 GB 32 GB 18 GB
wizard-math7bDec/2023 WizardLM Team (Microsoft Research) USA16 GB 8 GB 4 GB
wizard-math13bDec/2023 WizardLM Team (Microsoft Research) USA16 GB 8 GB 7 GB
wizard-math70bDec/2023 WizardLM Team (Microsoft Research) USA128 GB 64 GB 38 GB
wizard-vicuna13bDec/2023 WizardLM Team (Microsoft Research) USA16 GB 8 GB 7 GB
wizard-vicuna-uncensored7bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 4 GB
wizard-vicuna-uncensored13bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 7 GB
wizard-vicuna-uncensored30bDec/2023 Eric Hartford (Independent) USA32 GB 16 GB 16 GB
wizardcoder33bDec/2023 WizardLM Team (Microsoft Research) USA64 GB 32 GB 18 GB
wizardlmUnknownDec/2023 WizardLM Team (Microsoft Research) USA8 GB 4 GB 1 GB
wizardlm-uncensored13bDec/2023 Eric Hartford (Independent) USA16 GB 8 GB 7 GB
wizardlm27bMar/2024 Microsoft USA16 GB 8 GB 4 GB
wizardlm28x22bMar/2024 Microsoft USA128 GB 64 GB 12 GB
xwinlm7bDec/2023 Xwin-LM Team China16 GB 8 GB 4 GB
xwinlm13bDec/2023 Xwin-LM Team China16 GB 8 GB 7 GB
yarn-llama27bDec/2023 Maxime Labonne (Independent) France16 GB 8 GB 4 GB
yarn-llama213bDec/2023 Maxime Labonne (Independent) France16 GB 8 GB 7 GB
yarn-mistral7bDec/2023 Maxime Labonne (Independent) France16 GB GB 4 GB