q5 0 - Robuta Search

https://ollama.com/library/dolphin-mistral:7b-v2.1-q5_0/blobs/f02dd72bb242 dolphin-mistral:7b-v2.1-q5_0/params The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8. mistral 7b q5 0 dolphin v2 1 https://ollama.com/mannix/llama3-groq-tool-8b:q5_0/blobs/d96d6a906f15 mannix/llama3-groq-tool-8b:q5_0/model A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling. q5 0 mannix groq tool 8b https://www.ollama.com/library/llama3.2:3b-text-q5_0/blobs/2d920f1b2f4f llama3.2:3b-text-q5_0/model Meta's Llama 3.2 goes small with 1B and 3B models. q5 0 2 3b text model https://ollama.com/library/granite3-dense:8b-instruct-q5_0/blobs/492069a62c25 granite3-dense:8b-instruct-q5_0/license The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code... q5 0 dense 8b instruct license https://ollama.com/library/starling-lm:7b-alpha-q5_0/blobs/f507449d49be starling-lm:7b-alpha-q5_0/params Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness. q5 0 starling lm 7b alpha https://ollama.com/mannix/llama3-groq-tool-8b:q5_0/blobs/56bb8bd477a5 mannix/llama3-groq-tool-8b:q5_0/params A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling. q5 0 mannix groq tool 8b https://ollama.com/library/internlm2:1.8b-chat-v2.5-q5_0/blobs/3e9c19662c62 internlm2:1.8b-chat-v2.5-q5_0/template InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. q5 0 internlm2 1 8b chat https://ollama.com/library/codegemma:7b-instruct-q5_0/blobs/109037bec39c codegemma:7b-instruct-q5_0/template CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation,... q5 0 7b instruct template https://ollama.com/mannix/gemma2-9b:q5_0/blobs/c827688e53c8 mannix/gemma2-9b:q5_0/template Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models q5 0 mannix gemma2 9b template https://www.ollama.com/library/llama3.2:3b-text-q5_0/blobs/fcc5a6bec9da llama3.2:3b-text-q5_0/license Meta's Llama 3.2 goes small with 1B and 3B models. q5 0 2 3b text license https://www.ollama.com/library/llama3.1:8b-text-q5_0/blobs/0ba8f0e314b4 llama3.1:8b-text-q5_0/license Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes. llama3 1 q5 0 8b text license https://ollama.com/library/llama2:7b-text-q5_0/blobs/defb76d1c464 llama2:7b-text-q5_0/model Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters. q5 0 llama2 7b text model https://www.ollama.com/library/llama3.3:70b-instruct-q5_0/blobs/948af2743fc7 llama3.3:70b-instruct-q5_0/template New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. q5 0 3 70b instruct template https://ollama.com/mannix/gemma2-9b:q5_0/blobs/cf79c765fe51 mannix/gemma2-9b:q5_0/model Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models q5 0 mannix gemma2 9b model https://ollama.com/library/internlm2:1.8b-chat-v2.5-q5_0/blobs/3f4e1276d8d4 internlm2:1.8b-chat-v2.5-q5_0/model InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. q5 0 internlm2 1 8b chat https://ollama.com/library/notux:8x7b-v1-q5_0/blobs/2b63975c3cbf notux:8x7b-v1-q5_0/model A top-performing mixture of experts model, fine-tuned with high-quality data. q5 0 v1 model https://www.ollama.com/library/llama3.3:70b-instruct-q5_0/blobs/bc371a43ce90 llama3.3:70b-instruct-q5_0/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. q5 0 3 70b instruct license https://ollama.com/mannix/llama3-groq-tool-8b:q5_0/blobs/d5f55f09bfc5 mannix/llama3-groq-tool-8b:q5_0/license A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling. q5 0 mannix groq tool 8b https://ollama.com/library/starcoder:15b-plus-q5_0/blobs/1576480a555b starcoder:15b-plus-q5_0/params StarCoder is a code generation model trained on 80+ programming languages. q5 0 15b plus params https://ollama.com/library/llama3.3:70b-instruct-q5_0/blobs/bc371a43ce90 llama3.3:70b-instruct-q5_0/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. q5 0 3 70b instruct license https://ollama.com/nqduc/mixsura:mixsura-q5_0/blobs/23c0efadfa5a nqduc/mixsura:mixsura-q5_0/model State-of-the-art MoE Large Language Model for Vietnamese q5 0 model https://ollama.com/library/internlm2:1.8b-chat-v2.5-q5_0/blobs/75357d685f23 internlm2:1.8b-chat-v2.5-q5_0/system InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. q5 0 internlm2 1 8b chat https://ollama.com/library/phi:2.7b-chat-v2-q5_0/blobs/7908abcab772 phi:2.7b-chat-v2-q5_0/license Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities. q5 0 phi 2 7b chat https://ollama.com/library/notux:8x7b-v1-q5_0/blobs/ed11eda7790d notux:8x7b-v1-q5_0/params A top-performing mixture of experts model, fine-tuned with high-quality data. q5 0 v1 params https://www.ollama.com/library/llama3.3:70b-instruct-q5_0/blobs/2c233fc8bf14 llama3.3:70b-instruct-q5_0/model New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. q5 0 3 70b instruct model https://ollama.com/library/mistral-openorca:7b-q5_0/blobs/de6bcd73f9b4 mistral-openorca:7b-q5_0/params Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset. q5 0 mistral 7b params https://ollama.com/library/dolphin-llama3:8b-v2.9-q5_0/blobs/9640c2212a51 dolphin-llama3:8b-v2.9-q5_0/system Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills. q5 0 dolphin 8b v2 9 https://ollama.com/library/notux:8x7b-v1-q5_0/blobs/79b7eca19f7a notux:8x7b-v1-q5_0/template A top-performing mixture of experts model, fine-tuned with high-quality data. q5 0 v1 template https://ollama.com/library/smollm2:135m-instruct-q5_0/blobs/58d1e17ffe51 smollm2:135m-instruct-q5_0/license SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. q5 0 instruct license https://ollama.com/library/meditron:7b-q5_0/blobs/e3d94d483bb9 meditron:7b-q5_0/system Open-source medical large language model adapted from Llama 2 to the medical domain. q5 0 meditron 7b system https://ollama.com/library/qwen2.5:3b-instruct-q5_0/blobs/b5c0e5cf74cf qwen2.5:3b-instruct-q5_0/license Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has... qwen2 5 q5 0 3b instruct license https://ollama.com/library/notux:8x7b-v1-q5_0/blobs/002c2696d92b notux:8x7b-v1-q5_0/license A top-performing mixture of experts model, fine-tuned with high-quality data. q5 0 v1 license https://ollama.com/mannix/gemma2-9b:q5_0/blobs/097a36493f71 mannix/gemma2-9b:q5_0/license Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models q5 0 mannix gemma2 9b license https://ollama.com/nqduc/mixsura:mixsura-q5_0/blobs/f2dd6363b7a7 nqduc/mixsura:mixsura-q5_0/system State-of-the-art MoE Large Language Model for Vietnamese q5 0 system https://ollama.com/library/internlm2:1.8b-chat-v2.5-q5_0/blobs/f02dd72bb242 internlm2:1.8b-chat-v2.5-q5_0/params InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. q5 0 internlm2 1 8b chat https://ollama.com/library/vicuna:33b-q5_0/blobs/4c0b4335e8a8 vicuna:33b-q5_0/model General use chat model based on Llama and Llama 2 with 2K to 16K context sizes. q5 0 vicuna 33b model https://www.ollama.com/library/llama3.3:70b-instruct-q5_0/blobs/53a87df39647 llama3.3:70b-instruct-q5_0/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. q5 0 3 70b instruct license https://ollama.com/library/starcoder:15b-plus-q5_0/blobs/4fead320b524 starcoder:15b-plus-q5_0/model StarCoder is a code generation model trained on 80+ programming languages. q5 0 15b plus model https://ollama.com/library/gemma:2b-instruct-q5_0/blobs/04fc459268c4 gemma:2b-instruct-q5_0/model Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1 q5 0 gemma 2b instruct model https://www.ollama.com/library/deepseek-coder-v2:236b-base-q5_0 deepseek-coder-v2:236b-base-q5_0 An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. deepseek coder v2 base q5 0 https://www.ollama.com/library/stablelm2:12b-chat-q5_0 stablelm2:12b-chat-q5_0 Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese,... 12b chat q5 0 https://www.adac.de/rund-ums-fahrzeug/autokatalog/marken-modelle/audi/q5/gu/344615/ Audi Q5 2.0 TDI MHEV plus quattro S tronic (ab 07/25): Technische Daten, Bilder, Preise | ADAC