pt to be in the following format: \n{instruction}\n{initial_code}\n{edit_snippet}\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","modality":"text->text","isMoe":false,"featured":null},{"id":"morph-v3-large","slug":"morph-v3-large","name":"Morph: Morph V3 Large","creator":"Morph","creatorSlug":"morph","releaseDate":"2025-07-07","qualityIndex":null,"codingIndex":null,"mathIndex":null,"benchmarks":{"mmluPro":null,"gpqa":null,"hle":null,"livecodebench":null,"scicode":null,"math500":null,"aime":null,"aime25":null,"ifbench":null,"lcr":null,"terminalbenchHard":null,"tau2":null},"inputPrice":0.8999999999999999,"outputPrice":1.9,"blendedPrice":1.15,"outputSpeed":null,"ttft":null,"ttfat":null,"isOpenSource":false,"parameterCount":null,"contextLength":262144,"maxOutputTokens":131072,"hfId":null,"hfDownloads30d":null,"hfLikes":null,"hfTrendingScore":null,"hfLicense":null,"orId":"morph/morph-v3-large","orProviderCount":null,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\n\nThe model requires the prompt to be in the following format: \n{instruction}\n{initial_code}\n{edit_snippet}\n\nZero Data Retention is enabled for Morph. Learn more about this model in their [documentation](https://docs.morphllm.com/quickstart)","modality":"text->text","isMoe":false,"featured":null},{"id":"mythomax-l2-13b","slug":"mythomax-l2-13b","name":"MythoMax 13B","creator":"Gryphe","creatorSlug":"gryphe","releaseDate":"2023-07-02","qualityIndex":null,"codingIndex":null,"mathIndex":null,"benchmarks":{"mmluPro":null,"gpqa":null,"hle":null,"livecodebench":null,"scicode":null,"math500":null,"aime":null,"aime25":null,"ifbench":null,"lcr":null,"terminalbenchHard":null,"tau2":null},"inputPrice":0.06,"outputPrice":0.06,"blendedPrice":0.06,"outputSpeed":null,"ttft":null,"ttfat":null,"isOpenSource":true,"parameterCount":null,"contextLength":4096,"maxOutputTokens":4096,"hfId":null,"hfDownloads30d":null,"hfLikes":null,"hfTrendingScore":null,"hfLicense":null,"orId":"gryphe/mythomax-l2-13b","orProviderCount":null,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","modality":"text->text","isMoe":false,"featured":null},{"id":"llama-3-1-nemotron-70b-instruct","slug":"llama-3-1-nemotron-70b-instruct","name":"NVIDIA: Llama 3.1 Nemotron 70B Instruct","creator":"NVIDIA","creatorSlug":"nvidia","releaseDate":"2024-10-15","qualityIndex":null,"codingIndex":null,"mathIndex":null,"benchmarks":{"mmluPro":null,"gpqa":null,"hle":null,"livecodebench":null,"scicode":null,"math500":null,"aime":null,"aime25":null,"ifbench":null,"lcr":null,"terminalbenchHard":null,"tau2":null},"inputPrice":1.2,"outputPrice":1.2,"blendedPrice":1.2,"outputSpeed":null,"ttft":null,"ttfat":null,"isOpenSource":true,"parameterCount":null,"contextLength":131072,"maxOutputTokens":16384,"hfId":null,"hfDownloads30d":null,"hfLikes":null,"hfTrendingScore":null,"hfLicense":null,"orId":"nvidia/llama-3.1-nemotron-70b-instruct","orProviderCount":null,"description":"NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels in automatic alignment benchmarks. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains.\n\nUsage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).","modality":"text->text","isMoe":false,"featured":null},{"id":"llama-3-1-nemotron-ultra-253b-v1","slug":"llama-3-1-nemotron-ultra-253b-v1","name":"NVIDIA: Llama 3.1 Nemotron Ultra 253B v1","creator":"NVIDIA","creatorSlug":"nvidia","releas

llava v1.6 mistral 7b hf

Model Family

Open Source

Quick Compare

Similar Models