qwen2 - Robuta Search

https://ollama.com/huihui_ai/qwen2.5-1m-abliterated:7b/blobs/99c3bddafb9c huihui_ai/qwen2.5-1m-abliterated:7b/model Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. qwen2 5 ai 1m 7b model https://ollama.com/huihui_ai/qwen2.5-1m-abliterated/blobs/eb4402837c78 huihui_ai/qwen2.5-1m-abliterated/template Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. qwen2 5 ai 1m template https://huggingface.co/spaces/Gradio-Community/hyperbolic-qwen2.5Coder-32B Hyperbolic Qwen2.5Coder 32B - a Hugging Face Space by Gradio-Community Enter your coding instructions, and get code snippets as a result. Perfect for generating code or solving coding problems. hugging face hyperbolic qwen2 32b https://ollama.com/library/qwen2.5-coder:14b-instruct-q3_K_S qwen2.5-coder:14b-instruct-q3_K_S The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 14b instruct q3 https://ollama.com/library/qwen2.5-coder:0.5b-instruct qwen2.5-coder:0.5b-instruct The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b instruct https://ollama.com/mannix/qwen2-math-1.5b:q5_1 mannix/qwen2-math-1.5b:q5_1 Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs math 1 mannix qwen2 5b q5 https://ollama.com/library/qwen2.5-coder:3b-instruct-q3_K_L/blobs/45fc3ea7579a qwen2.5-coder:3b-instruct-q3_K_L/license The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 k l coder 3b instruct https://wandb.ai/byyoung3/ml-news/reports/Qwen2-5-VL-32B-A-Leaner-Smarter-Multimodal-Model-for-Visual-Reasoning---VmlldzoxMTk2Nzk0NA Qwen2.5-VL-32B: A Leaner, Smarter Multimodal Model for Visual Reasoning qwen2 5 https://ollama.com/library/qwen2.5-coder:0.5b-base-q4_K_M qwen2.5-coder:0.5b-base-q4_K_M The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b base https://ollama.com/goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/blobs/b834cc289834 goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/system Qwen2.5, but Josiefied and uncensored. qwen2 5 7b system https://ollama.com/library/qwen2.5:0.5b-instruct-q5_1/blobs/832dd9e00a68 qwen2.5:0.5b-instruct-q5_1/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 0 5b instruct q5 https://openrouter.ai/eva-unit-01/eva-qwen-2.5-72b EVA Qwen2.5 72B - API Pricing & Providers | OpenRouter EVA Qwen2.5 72B is a roleplay and storywriting specialist model. 32,000 token context window. qwen2 5 api pricing eva 72b providers https://huggingface.co/spaces/Pavantej/qwen2-titans-miras Qwen2 Titans MIRAS - a Hugging Face Space by Pavantej This application generates text by enhancing the understanding of previous interactions, allowing for more coherent and contextually relevant responses. Users... hugging face qwen2 titans miras space https://ollama.com/mannix/qwen2-math-1.5b:q4_1 mannix/qwen2-math-1.5b:q4_1 Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs math 1 mannix qwen2 5b q4 https://ollama.com/library/qwen2.5:1.5b-instruct-q8_0 qwen2.5:1.5b-instruct-q8_0 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 1 5b instruct q8 https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct Qwen2.5 Coder 32B Instruct - API Pricing & Benchmarks | OpenRouter Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). $0.66 per million input tokens, $1 per million... qwen2 5 api pricing coder 32b instruct https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q4_k_m mannix/dolphin-2.9.2-qwen2-72b:q4_k_m This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2.5-coder:32b-instruct-q8_0/blobs/e94a8ecb9327 qwen2.5-coder:32b-instruct-q8_0/template The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b instruct q8 https://ollama.com/library/qwen2.5:0.5b-instruct-q5_1/blobs/66b9ea09bd5b qwen2.5:0.5b-instruct-q5_1/system 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 0 5b instruct q5 https://ollama.com/mannix/qwen2-0.5b:q5_1 mannix/qwen2-0.5b:q5_1 Qwen2 is the new series of Qwen large language models mannix qwen2 0 5b q5 https://simonwillison.net/2024/Sep/4/qwen2-vl/ Qwen2-VL: To See the World More Clearly Qwen is Alibaba Cloud's organization training LLMs. Their latest model is Qwen2-VL - a vision LLM - and it's getting some really positive buzz. Here's a... see the world qwen2 vl clearly https://ollama.com/mannix/qwen2-0.5b:latest mannix/qwen2-0.5b Qwen2 is the new series of Qwen large language models mannix qwen2 0 5b https://ollama.com/goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/blobs/8d55d9b7c696 goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/model Qwen2.5, but Josiefied and uncensored. qwen2 5 7b model https://ollama.com/library/qwen2.5-coder:0.5b-base-q3_K_M qwen2.5-coder:0.5b-base-q3_K_M The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b base https://ollama.com/library/qwen2.5-coder:32b-instruct-q5_1 qwen2.5-coder:32b-instruct-q5_1 The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b instruct q5 https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:iq3_xxs mannix/dolphin-2.9.2-qwen2-72b:iq3_xxs This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2.5vl:7b-q4_K_M/blobs/52d2a7aa3a38 qwen2.5vl:7b-q4_K_M/params Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. k m qwen2 7b q4 params https://ollama.com/library/qwen2.5vl:7b/blobs/832dd9e00a68 qwen2.5vl:7b/license Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 7b license https://ollama.com/library/qwen2.5vl:3b-fp16 qwen2.5vl:3b-fp16 Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 3b fp16 https://geekflare.com/news/qwen2-5-omni-7b-the-ai-that-understands-everything/ Qwen2.5-Omni-7B: The AI That Understands Everything? Mar 27, 2025 - Alibaba has unveiled Qwen2.5-Omni-7B. It's an open-source multimodal AI model designed to process and generate text, audio, images, and video. qwen2 5 omni 7b ai understands https://huggingface.co/collections/DrNicefellow/qwen25-32b-instruct-exl2 Qwen2.5-32B-Instruct-exl2 - a DrNicefellow Collection Unlock the magic of AI with handpicked models, awesome datasets, papers, and mind-blowing Spaces from DrNicefellow qwen2 5 32b instruct collection https://www.kaggle.com/models/keras/qwen2-5-math/keras/qwen2.5_math_7b_en/1 Keras | Qwen2.5-Math | Kaggle Advanced Bilingual Mathematical Reasoning via Chain-of-Thought and Tool-Integrated Logic. Qwen2.5-Math is the latest series of Qwen large language models. qwen2 5 keras math kaggle https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q5_0 mannix/dolphin-2.9.2-qwen2-72b:q5_0 This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2.5vl:3b-fp16/blobs/75357d685f23 qwen2.5vl:3b-fp16/system Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 3b fp16 system https://ollama.com/goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/blobs/9bebd78bf5bc goekdenizguelmez/JOSIEFIED-Qwen2.5:7b/template Qwen2.5, but Josiefied and uncensored. qwen2 5 7b template https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q4_1 mannix/dolphin-2.9.2-qwen2-72b:q4_1 This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://openrouter.ai/qwen/qwen-2.5-72b-instruct/apps Apps Using Qwen2.5 72B Instruct | OpenRouter See apps that are using Qwen2.5 72B Instruct - Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon... qwen2 5 apps using 72b instruct https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:latest mannix/dolphin-2.9.2-qwen2-72b This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://openrouter.ai/qwen/qwen-2.5-7b-instruct Qwen2.5 7B Instruct - API Pricing & Providers | OpenRouter Qwen2.5 7B is the latest series of Qwen large language models. $0.04 per million input tokens, $0.10 per million output tokens. 32,768 token context window,... qwen2 5 api pricing 7b instruct providers https://ollama.com/library/qwen2.5:72b qwen2.5:72b 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 72b https://ollama.com/library/qwen2.5-coder:1.5b-base-q3_K_M qwen2.5-coder:1.5b-base-q3_K_M The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 1 5b base https://ollama.com/mannix/qwen2-math-1.5b:latest mannix/qwen2-math-1.5b Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs math 1 mannix qwen2 5b https://arxiv.org/html/2409.12186v1 Qwen2.5-Coder Technical Report qwen2 5 coder technical report https://ollama.com/org/qwen2.5-1m:7b org/qwen2.5-1m:7b The long-context version of Qwen2.5, supporting 1M-token context lengths qwen2 5 1m 7b https://ollama.com/mannix/qwen2-0.5b:iq4_nl mannix/qwen2-0.5b:iq4_nl Qwen2 is the new series of Qwen large language models mannix qwen2 0 5b nl https://huggingface.co/collections/DrNicefellow/qwen25-coder-14b-instruct-exl2 Qwen2.5-Coder-14B-Instruct-exl2 - a DrNicefellow Collection Unlock the magic of AI with handpicked models, awesome datasets, papers, and mind-blowing Spaces from DrNicefellow qwen2 5 coder 14b instruct collection https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q4_0 mannix/dolphin-2.9.2-qwen2-72b:q4_0 This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2.5-coder:0.5b-base-q4_K_S qwen2.5-coder:0.5b-base-q4_K_S The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b base https://ollama.com/trollek/qwen2-diffusion-prompter:v01-q5_K_S/blobs/9326415655df trollek/qwen2-diffusion-prompter:v01-q5_K_S/model Prompt helper for Stable Diffusion based on Qwen2-0.5B k s qwen2 diffusion prompter v01 https://ollama.com/trollek/qwen2-diffusion-prompter:v01-q6_K/blobs/5865c046591f trollek/qwen2-diffusion-prompter:v01-q6_K/params Prompt helper for Stable Diffusion based on Qwen2-0.5B qwen2 diffusion prompter v01 q6 https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct?tab=parameters Qwen2.5 VL 72B Instruct - API Pricing & Providers | OpenRouter Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. $0.25 per million input tokens, $0.75 per million output... qwen2 5 api pricing vl 72b instruct https://ollama.com/library/qwen2.5:3b-instruct-q4_1/blobs/b3c2ba74b47e qwen2.5:3b-instruct-q4_1/model 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 q4 1 3b instruct model https://ollama.com/library/qwen2.5vl:7b-fp16/blobs/a242d8dfdc8f qwen2.5vl:7b-fp16/template Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 7b fp16 template https://ollama.com/library/qwen2.5:14b-instruct-q5_K_S qwen2.5:14b-instruct-q5_K_S 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 14b instruct q5 k https://ollama.com/library/qwen2.5-coder:32b-base-q4_K_S qwen2.5-coder:32b-base-q4_K_S The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b base q4 https://ollama.com/library/qwen2.5:3b-instruct-q8_0/blobs/66b9ea09bd5b qwen2.5:3b-instruct-q8_0/system 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 3b instruct q8 0 https://openrouter.ai/compare/qwen/qwen2.5-vl-32b-instruct Qwen2.5 VL 32B Instruct compared to other AI models | OpenRouter Compare Qwen2.5 VL 32B Instruct from Qwen to other AI models on key metrics including benchmarks, price, context length, and other model features. qwen2 5 ai models vl 32b instruct https://openrouter.ai/qwen/qwen-2.5-vl-7b-instruct Qwen2.5-VL 7B Instruct - API Pricing & Providers | OpenRouter qwen2 5 api pricing vl 7b instruct https://ollama.com/library/qwen2.5:72b-instruct-q5_1/blobs/b5c0e5cf74cf qwen2.5:72b-instruct-q5_1/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 72b instruct q5 1 https://ollama.com/library/qwen2:1.5b-instruct-q8_0 qwen2:1.5b-instruct-q8_0 Qwen2 is a new series of large language models from Alibaba group qwen2 1 5b instruct q8 https://ollama.com/library/qwen2.5:3b-instruct-q8_0/blobs/eb4402837c78 qwen2.5:3b-instruct-q8_0/template 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 3b instruct q8 0 https://ollama.com/huihui_ai/qwen2.5-1m-abliterated:7b/blobs/832dd9e00a68 huihui_ai/qwen2.5-1m-abliterated:7b/license Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. qwen2 5 ai 1m 7b license https://ollama.com/library/qwen2.5:3b-instruct-q5_1/blobs/e52bf6516154 qwen2.5:3b-instruct-q5_1/model 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 3b instruct q5 1 https://ollama.com/library/qwen2:72b-text-q4_0/blobs/3123145c9f9c qwen2:72b-text-q4_0/model Qwen2 is a new series of large language models from Alibaba group qwen2 72b text q4 0 https://ollama.com/trollek/qwen2-diffusion-prompter:v01-q5_K_S/blobs/5865c046591f trollek/qwen2-diffusion-prompter:v01-q5_K_S/params Prompt helper for Stable Diffusion based on Qwen2-0.5B k s qwen2 diffusion prompter v01 https://openrouter.ai/compare/qwen/qwen2.5-coder-7b-instruct Qwen2.5 Coder 7B Instruct compared to other AI models | OpenRouter Compare Qwen2.5 Coder 7B Instruct from Qwen to other AI models on key metrics including benchmarks, price, context length, and other model features. qwen2 5 ai models coder 7b instruct https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q5_1 mannix/dolphin-2.9.2-qwen2-72b:q5_1 This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2:0.5b-instruct-q8_0 qwen2:0.5b-instruct-q8_0 Qwen2 is a new series of large language models from Alibaba group qwen2 0 5b instruct q8 https://ollama.com/library/qwen2.5vl:72b-fp16 qwen2.5vl:72b-fp16 Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 72b fp16 https://ollama.com/library/qwen2-math:1.5b-instruct-q8_0/blobs/f02dd72bb242 qwen2-math:1.5b-instruct-q8_0/params Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of... math 1 qwen2 5b instruct q8 https://ollama.com/goekdenizguelmez/JOSIEFIED-Qwen2.5 goekdenizguelmez/JOSIEFIED-Qwen2.5 Qwen2.5, but Josiefied and uncensored. qwen2 5 https://ollama.com/mannix/qwen2-0.5b:q5_0 mannix/qwen2-0.5b:q5_0 Qwen2 is the new series of Qwen large language models mannix qwen2 0 5b q5 https://ollama.com/library/qwen2-math:1.5b-instruct-q5_0 qwen2-math:1.5b-instruct-q5_0 Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of... math 1 qwen2 5b instruct q5 https://ollama.com/library/qwen2.5:0.5b qwen2.5:0.5b 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 0 5b https://ollama.com/library/qwen2.5-coder:32b-instruct-q5_K_M qwen2.5-coder:32b-instruct-q5_K_M The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b instruct q5 https://ollama.com/trollek/qwen2-diffusion-prompter:latest trollek/qwen2-diffusion-prompter Prompt helper for Stable Diffusion based on Qwen2-0.5B qwen2 diffusion prompter https://ollama.com/library/qwen2.5:7b qwen2.5:7b 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 7b https://ollama.com/library/qwen2.5vl:7b/blobs/a242d8dfdc8f qwen2.5vl:7b/template Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 7b template https://ollama.com/library/qwen2.5:0.5b-instruct-q6_K qwen2.5:0.5b-instruct-q6_K 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 0 5b instruct q6 https://ollama.com/trollek/qwen2-diffusion-prompter:v01-q6_K/blobs/3383b952b5f9 trollek/qwen2-diffusion-prompter:v01-q6_K/model Prompt helper for Stable Diffusion based on Qwen2-0.5B qwen2 diffusion prompter v01 q6 https://www.ollama.com/library/qwen2-math qwen2-math Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of... qwen2 math https://ollama.com/library/qwen2.5-coder:32b-instruct qwen2.5-coder:32b-instruct The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b instruct https://ollama.com/library/qwen2.5-coder:7b-base/blobs/0aa0872a8ea3 qwen2.5-coder:7b-base/model The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 7b base model https://ollama.com/library/qwen2.5vl:32b-q4_K_M/blobs/75357d685f23 qwen2.5vl:32b-q4_K_M/system Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. k m qwen2 32b q4 system https://ollama.com/library/qwen2:0.5b-instruct-q2_K/blobs/f02dd72bb242 qwen2:0.5b-instruct-q2_K/params Qwen2 is a new series of large language models from Alibaba group qwen2 0 5b instruct q2 https://ollama.com/library/qwen2.5-coder:32b-instruct-fp16/blobs/66b9ea09bd5b qwen2.5-coder:32b-instruct-fp16/system The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 32b instruct fp16 https://ollama.com/library/qwen2.5:72b/blobs/6e7fdda508e9 qwen2.5:72b/model 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 72b model https://ollama.com/sammcj/qwen2.5-coder-7b-instruct sammcj/qwen2.5-coder-7b-instruct Qwen 2.5 Coder 7b Instruct qwen2 5 coder 7b instruct https://ollama.com/library/qwen2.5:7b-instruct-q6_K qwen2.5:7b-instruct-q6_K 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 7b instruct q6 k https://simonwillison.net/2025/Apr/28/qwen25-omni/ Qwen2.5 Omni: See, Hear, Talk, Write, Do It All! I'm not sure how I missed this one at the time, but last month (March 27th) Qwen released their first multi-modal model that can handle audio and video in... qwen2 5 see hear do it omni talk https://ollama.com/library/qwen2.5-coder:0.5b-instruct-fp16 qwen2.5-coder:0.5b-instruct-fp16 The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b instruct https://ollama.com/library/qwen2.5-coder:0.5b-base-fp16 qwen2.5-coder:0.5b-base-fp16 The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing. qwen2 5 coder 0 5b base https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:q2_k mannix/dolphin-2.9.2-qwen2-72b:q2_k This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2:0.5b-instruct-q2_K/blobs/7d16a83e9278 qwen2:0.5b-instruct-q2_K/model Qwen2 is a new series of large language models from Alibaba group qwen2 0 5b instruct q2 https://ollama.com/vanilj/qwen2.5-72b-instruct-iq3_xxs/blobs/f02dd72bb242 vanilj/qwen2.5-72b-instruct-iq3_xxs/params Qwen2.5 is the latest series of Qwen large language models. qwen2 5 72b instruct iq3 xxs https://ollama.com/library/qwen2:1.5b-instruct-q8_0/blobs/62fbfd9ed093 qwen2:1.5b-instruct-q8_0/template Qwen2 is a new series of large language models from Alibaba group qwen2 1 5b instruct q8 https://ollama.com/mannix/dolphin-2.9.2-qwen2-72b:iq4_nl mannix/dolphin-2.9.2-qwen2-72b:iq4_nl This model is based on Qwen2-72b, Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and... 2 9 mannix dolphin qwen2 72b https://ollama.com/library/qwen2:7b-instruct-q5_K_S/blobs/c156170b718e qwen2:7b-instruct-q5_K_S/license Qwen2 is a new series of large language models from Alibaba group k s qwen2 7b instruct q5 https://ollama.com/library/qwen2.5vl:3b-q8_0/blobs/832dd9e00a68 qwen2.5vl:3b-q8_0/license Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL. qwen2 3b q8 0 license https://ollama.com/library/qwen2.5:7b-instruct-q3_K_M/blobs/427b3d95aca8 qwen2.5:7b-instruct-q3_K_M/model 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 k m 7b instruct q3