fp16 - Robuta Search

https://ollama.com/library/qwen:14b-chat-v1.5-fp16 qwen:14b-chat-v1.5-fp16 Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters qwen 14b chat v1 5 https://ollama.com/library/llama3.3:70b-instruct-fp16/blobs/53a87df39647 llama3.3:70b-instruct-fp16/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 license https://ollama.com/library/mistral:7b-instruct-fp16/blobs/22e1b2e8dc2f mistral:7b-instruct-fp16/template The 7B model released by Mistral AI, updated to version 0.3. mistral 7b instruct fp16 template https://civitai.com/models/330313/ttplanetsdxlcontrolnettilerealistic TTPLanet_SDXL_Controlnet_Tile_Realistic - v2.0_fp16 | Stable Diffusion XL Controlnet | Civitai Thanks for your attention. contact me if you want, discord with "ttplanet", Civitai with "ttplanet" you can also join the group discussion with QQ ... stable diffusion xl v2 0 https://ollama.com/library/qwen3:14b-fp16/blobs/d18a5cc71b84 qwen3:14b-fp16/license Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 14b fp16 license https://ollama.com/library/codellama:70b-instruct-fp16 codellama:70b-instruct-fp16 A large language model that can use text prompts to generate and discuss code. codellama 70b instruct fp16 https://www.ollama.com/library/qwen3:14b-fp16 qwen3:14b-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 14b fp16 https://www.ollama.com/library/llama-pro:8b-text-fp16 llama-pro:8b-text-fp16 An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and... llama pro 8b text fp16 https://ollama.com/library/qwen3:4b-thinking-2507-fp16/blobs/0c5b43627b54 qwen3:4b-thinking-2507-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 4b thinking 2507 fp16 https://ollama.com/library/dolphin-llama3:8b-v2.9-fp16 dolphin-llama3:8b-v2.9-fp16 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. dolphin 8b v2 9 fp16 https://www.ollama.com/library/llama3.3:70b-instruct-fp16/blobs/a8da3fb9eb71 llama3.3:70b-instruct-fp16/model New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 model https://ollama.com/library/qwen3:235b-a22b-thinking-2507-fp16/blobs/2d54db2b9bb2 qwen3:235b-a22b-thinking-2507-fp16/template Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 thinking 2507 fp16 template https://ollama.com/library/codeqwen:7b-chat-v1.5-fp16 codeqwen:7b-chat-v1.5-fp16 CodeQwen1.5 is a large language model pretrained on a large amount of code data. 7b chat v1 5 fp16 https://civitai.com/models/117188/reviews?modelVersionId=129581&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&reviewId=45539180 SDXL_fixedvae_fp16(Remove Watermark) Reviews | Rated 4.99 Stars by 185 Users on Civitai Explore user reviews of the SDXL_fixedvae_fp16(Remove Watermark) AI model on Civitai, rated 4.99 stars by 185 users, and see how it has helped others bring... https://civitai.com/models/117188/reviews?modelVersionId=129581&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&reviewId=55397001 SDXL_fixedvae_fp16(Remove Watermark) Reviews | Rated 4.99 Stars by 185 Users on Civitai Explore user reviews of the SDXL_fixedvae_fp16(Remove Watermark) AI model on Civitai, rated 4.99 stars by 185 users, and see how it has helped others bring... https://ollama.com/library/internlm2:7b-chat-v2.5-fp16/blobs/c71d239df917 internlm2:7b-chat-v2.5-fp16/license InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. internlm2 7b chat v2 5 https://www.ollama.com/library/qwen3:235b-a22b-fp16 qwen3:235b-a22b-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 fp16 https://civitai.com/models/167318/ultra-realistic-by-stable-yogi-pony Ultra Realistic By Stable Yogi (Pony) - V2.0_FP16 | Pony Diffusion Checkpoint | Civitai Join me on Patreon for exclusive perks and early access to unique resources. To discuss custom LoRa's or models, feel free to connect on Discord. M... ultra realistic https://ollama.com/library/deepseek-r1:70b-llama-distill-fp16/blobs/6e4c38e1172f deepseek-r1:70b-llama-distill-fp16/license DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro. deepseek r1 70b llama distill fp16 https://ollama.com/library/mistral:7b-instruct-fp16/blobs/43070e2d4e53 mistral:7b-instruct-fp16/license The 7B model released by Mistral AI, updated to version 0.3. mistral 7b instruct fp16 license https://ollama.com/library/llama3.2:3b-text-fp16/blobs/fcc5a6bec9da llama3.2:3b-text-fp16/license Meta's Llama 3.2 goes small with 1B and 3B models. 2 3b text fp16 license https://ollama.com/library/codellama:34b-python-fp16 codellama:34b-python-fp16 A large language model that can use text prompts to generate and discuss code. codellama 34b python fp16 https://ollama.com/library/gemma3:12b-it-fp16/blobs/e0a42594d802 gemma3:12b-it-fp16/template The current, most capable model that runs on a single GPU. gemma3 12b fp16 template https://ollama.com/library/qwen3:30b-a3b-instruct-2507-fp16/blobs/eade0a07cac7 qwen3:30b-a3b-instruct-2507-fp16/template Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 30b a3b instruct 2507 https://www.ollama.com/library/tinyllama:1.1b-chat-v0.6-fp16 tinyllama:1.1b-chat-v0.6-fp16 The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens. 1 chat v0 6 https://civitai.com/models/1459741/asian-realism-by-stable-yogi-illus?modelVersionId=1849702 Asian Realism By Stable Yogi (ILLUS) - V2.0_FP16 | Illustrious Checkpoint | Civitai Join me on Patreon for exclusive Pro Models, workflows and Lora's and early access to unique resources. To commission LoRa's or checkpoint, feel fr... https://ollama.com/library/qwen3:4b-fp16/blobs/cff3f395ef37 qwen3:4b-fp16/params Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 4b fp16 params https://www.ollama.com/library/qwen3:235b-a22b-thinking-2507-fp16 qwen3:235b-a22b-thinking-2507-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 thinking 2507 fp16 https://www.ollama.com/library/nemotron:70b-instruct-fp16 nemotron:70b-instruct-fp16 Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries. nemotron 70b instruct fp16 https://www.ollama.com/library/sqlcoder:15b-fp16 sqlcoder:15b-fp16 SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks 15b fp16 https://ollama.com/library/qwen3:30b-a3b-thinking-2507-fp16/blobs/6c370d78fc31 qwen3:30b-a3b-thinking-2507-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 30b a3b thinking 2507 https://ollama.com/library/phind-codellama:34b-v2-fp16 phind-codellama:34b-v2-fp16 Code generation model based on Code Llama. phind codellama 34b v2 fp16 https://ollama.com/library/nous-hermes2:34b-yi-fp16 nous-hermes2:34b-yi-fp16 The powerful family of models by Nous Research that excels at scientific discussion and coding tasks. nous 34b yi fp16 https://mail-archive.com/cfe-commits@lists.llvm.org/msg680844.html [clang] [CIR][AArch64] Lower FP16 vduph lane intrinsics (PR #186955) clang cir aarch64 lower fp16 https://ollama.com/library/qwen3:0.6b-fp16/blobs/ae370d884f10 qwen3:0.6b-fp16/template Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 0 6b fp16 template https://ollama.com/library/falcon3:10b-instruct-fp16 falcon3:10b-instruct-fp16 A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques. 10b instruct fp16 https://www.ollama.com/library/llama3.3:70b-instruct-fp16/blobs/bc371a43ce90 llama3.3:70b-instruct-fp16/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 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://ollama.com/library/starcoder:15b-plus-fp16/blobs/1576480a555b starcoder:15b-plus-fp16/params StarCoder is a code generation model trained on 80+ programming languages. 15b plus fp16 params https://ollama.com/library/gemma:7b-instruct-fp16 gemma:7b-instruct-fp16 Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1 gemma 7b instruct fp16 https://ollama.com/mannix/gemma2-9b:fp16/blobs/1f0c17ce1cdb mannix/gemma2-9b:fp16/params 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 mannix gemma2 9b fp16 params https://www.ollama.com/library/smallthinker:3b-preview-fp16 smallthinker:3b-preview-fp16 A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. 3b preview fp16 https://ollama.com/library/codellama:13b-python-fp16 codellama:13b-python-fp16 A large language model that can use text prompts to generate and discuss code. codellama 13b python fp16 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/library/phi3:3.8b-mini-128k-instruct-fp16 phi3:3.8b-mini-128k-instruct-fp16 Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft. 3 8b phi3 mini 128k instruct https://ollama.com/library/qwen3:32b-fp16/blobs/cff3f395ef37 qwen3:32b-fp16/params Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 32b fp16 params https://www.ollama.com/library/qwen3:0.6b-fp16 qwen3:0.6b-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 0 6b fp16 https://civitai.com/models/58772/chillymix?modelVersionId=63220 ChillyMix - chillymix-V1-Fp16 | Stable Diffusion 1.x Checkpoint | Civitai This is another attempt to make a free/open version of the ChilloutMix. If you like my work, feel free to buy me a coffee at ko-fi. https://ko-fi.c... stable diffusion 1 v1 fp16 x checkpoint https://www.ollama.com/library/llama3.3:70b-instruct-fp16/blobs/948af2743fc7 llama3.3:70b-instruct-fp16/template New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 template https://ollama.com/library/nemotron:70b-instruct-fp16/blobs/56bb8bd477a5 nemotron:70b-instruct-fp16/params Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries. nemotron 70b instruct fp16 params https://ollama.com/library/deepseek-r1:70b-llama-distill-fp16/blobs/c5ad996bda6e deepseek-r1:70b-llama-distill-fp16/template DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro. deepseek r1 70b llama distill fp16 https://www.ollama.com/library/qwen3:8b-fp16 qwen3:8b-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 8b fp16 https://ollama.com/library/nous-hermes:70b-llama2-fp16/blobs/0ba4455c4f46 nous-hermes:70b-llama2-fp16/template General use models based on Llama and Llama 2 from Nous Research. nous hermes 70b llama2 fp16 https://civitai.com/models/672618/flux1devasian Flux.1[dev]Asian - v1.0-FP16 | Flux.1 Checkpoint | Civitai This is an experimental merged model that incorporates an Asian Lora I retrained. Tips:The checkpoint is compatible with other Flux.1 Dev Loras, bu... flux 1 dev asian v1 0 fp16 https://ollama.com/library/nemotron:70b-instruct-fp16/blobs/4863fe3335f3 nemotron:70b-instruct-fp16/template Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries. nemotron 70b instruct fp16 template https://ollama.com/library/qwen3:4b-fp16/blobs/ae370d884f10 qwen3:4b-fp16/template Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 4b fp16 template https://ollama.com/library/codeqwen:7b-code-v1.5-fp16 codeqwen:7b-code-v1.5-fp16 CodeQwen1.5 is a large language model pretrained on a large amount of code data. 7b code v1 5 fp16 https://ollama.com/library/nous-hermes2-mixtral:8x7b-dpo-fp16/blobs/1691af48af21 nous-hermes2-mixtral:8x7b-dpo-fp16/system The Nous Hermes 2 model from Nous Research, now trained over Mixtral. mixtral 8x7b nous dpo fp16 system https://ollama.com/library/qwen3:32b-fp16/blobs/50c6fb7ac4eb qwen3:32b-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 32b fp16 model https://ollama.com/library/deepseek-v3:671b-fp16 deepseek-v3:671b-fp16 A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. deepseek v3 671b fp16 https://www.ollama.com/library/deepseek-coder-v2:236b-base-fp16 deepseek-coder-v2:236b-base-fp16 An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. deepseek coder v2 base fp16 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/codellama:70b-python-fp16 codellama:70b-python-fp16 A large language model that can use text prompts to generate and discuss code. codellama 70b python fp16 https://www.ollama.com/library/stable-beluga:70b-fp16 stable-beluga:70b-fp16 Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy. stable beluga 70b fp16 https://ollama.com/library/stablelm2:12b-chat-fp16 stablelm2:12b-chat-fp16 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 fp16 https://ollama.com/mannix/gemma2-9b:fp16/blobs/097a36493f71 mannix/gemma2-9b:fp16/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 mannix gemma2 9b fp16 license https://ollama.com/library/nous-hermes:13b-fp16/blobs/0ba4455c4f46 nous-hermes:13b-fp16/template General use models based on Llama and Llama 2 from Nous Research. nous hermes 13b fp16 template https://ollama.com/library/qwen3:4b-instruct-2507-fp16/blobs/0914c7781e00 qwen3:4b-instruct-2507-fp16/params Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 4b instruct 2507 fp16 https://ollama.com/library/mistral-large:123b-instruct-2411-fp16 mistral-large:123b-instruct-2411-fp16 Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and... mistral large 123b instruct 2411 fp16 https://civitai.com/models/118312/xl3-experimental-sd10-xl-fp16 XL3 - Experimental SD1.0 XL FP16 - v1.0 | Stable Diffusion XL Checkpoint | Civitai This is a merge between the XL 1.0 base model and the refiner, also I merged in the offset Lora directly. In my opinion it can sometimes create bet... stable diffusion experimental sd1 0 xl https://civitai.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin?modelVersionId=155933 FIX FP16 Errors SDXL - Lower Memory use! --- sdxl-vae-fp16-fix by madebyollin - v1.0 | Stable... "As good as SDXL VAE but runs twice as fast and uses significantly less memory." https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7... https://ollama.com/library/qwen3:30b-a3b-fp16/blobs/ae370d884f10 qwen3:30b-a3b-fp16/template Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 30b a3b fp16 template https://www.ollama.com/library/deepseek-r1:14b-qwen-distill-fp16 deepseek-r1:14b-qwen-distill-fp16 DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro. deepseek r1 14b qwen distill fp16 https://ollama.com/library/qwen3:0.6b-fp16/blobs/cff3f395ef37 qwen3:0.6b-fp16/params Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 0 6b fp16 params https://civitai.com/models/117188/reviews?modelVersionId=129581&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&reviewId=36754337 SDXL_fixedvae_fp16(Remove Watermark) Reviews | Rated 4.99 Stars by 185 Users on Civitai Explore user reviews of the SDXL_fixedvae_fp16(Remove Watermark) AI model on Civitai, rated 4.99 stars by 185 users, and see how it has helped others bring... https://ollama.com/library/deepseek-r1:8b-llama-distill-fp16/blobs/f4d24e9138dd deepseek-r1:8b-llama-distill-fp16/params DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro. deepseek r1 8b llama distill fp16 https://ollama.com/library/qwen3:8b-fp16/blobs/cff3f395ef37 qwen3:8b-fp16/params Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 8b fp16 params https://ollama.com/library/stablelm2:1.6b-zephyr-fp16 stablelm2:1.6b-zephyr-fp16 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,... 1 6b zephyr https://civitai.com/models/140686/fix-fp16-errors-sdxl-lower-memory-use-sdxl-vae-fp16-fix-by-madebyollin FIX FP16 Errors SDXL - Lower Memory use! --- sdxl-vae-fp16-fix by madebyollin - v1.0 | Stable... "As good as SDXL VAE but runs twice as fast and uses significantly less memory." https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7... https://www.ollama.com/library/phi4:14b-fp16 phi4:14b-fp16 Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft. 14b fp16 https://ollama.com/library/meditron:7b-fp16/blobs/a47b02e00552 meditron:7b-fp16/template Open-source medical large language model adapted from Llama 2 to the medical domain. meditron 7b fp16 template https://www.ollama.com/library/qwen3:4b-thinking-2507-fp16 qwen3:4b-thinking-2507-fp16 Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 4b thinking 2507 fp16 https://civitai.com/models/1022641/helheim-flux Helheim Flux - v2.95 (FP16 AIO) | Flux.1 Checkpoint | Civitai Helheim is the realm of Hel, the goddess of death, in Norse mythology. Most people end up there after they have shuffled off this mortal coil... th... aio 1 helheim flux v2 95 https://civitai.com/models/117188/reviews?modelVersionId=129581&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&dialog=resourceReview&reviewId=40324899 SDXL_fixedvae_fp16(Remove Watermark) Reviews | Rated 4.99 Stars by 185 Users on Civitai Explore user reviews of the SDXL_fixedvae_fp16(Remove Watermark) AI model on Civitai, rated 4.99 stars by 185 users, and see how it has helped others bring... https://ollama.com/library/qwen3:0.6b-fp16/blobs/bc2421370aa0 qwen3:0.6b-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 0 6b fp16 model 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/qwen3:235b-a22b-thinking-2507-fp16/blobs/17ed41c74bdf qwen3:235b-a22b-thinking-2507-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 thinking 2507 fp16 model https://ollama.com/library/internlm2:7b-chat-v2.5-fp16/blobs/75357d685f23 internlm2:7b-chat-v2.5-fp16/system InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability. internlm2 7b chat v2 5 https://ollama.com/library/qwen3:235b-a22b-fp16/blobs/7e0e3743ff1f qwen3:235b-a22b-fp16/model Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 fp16 model https://www.ollama.com/library/nomic-embed-text:137m-v1.5-fp16/blobs/970aa74c0a90 nomic-embed-text:137m-v1.5-fp16/model A high-performing open embedding model with a large token context window. nomic embed text v1 5 https://www.ollama.com/library/llama3.3:70b-instruct-fp16/blobs/56bb8bd477a5 llama3.3:70b-instruct-fp16/params New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 params https://ollama.com/library/llama3.2:3b-text-fp16/blobs/bce7f0f4ece2 llama3.2:3b-text-fp16/model Meta's Llama 3.2 goes small with 1B and 3B models. 2 3b text fp16 model https://ollama.com/library/falcon3:1b-instruct-fp16 falcon3:1b-instruct-fp16 A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques. 1b instruct fp16 https://www.ollama.com/library/tinyllama:1.1b-chat-v1-fp16 tinyllama:1.1b-chat-v1-fp16 The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens. 1 chat https://ollama.com/library/qwen3:235b-a22b-fp16/blobs/d18a5cc71b84 qwen3:235b-a22b-fp16/license Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. qwen3 fp16 license https://www.ollama.com/library/llama3.3:70b-instruct-fp16/blobs/53a87df39647 llama3.3:70b-instruct-fp16/license New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model. 3 70b instruct fp16 license https://ollama.com/library/vicuna:7b-v1.5-fp16 vicuna:7b-v1.5-fp16 General use chat model based on Llama and Llama 2 with 2K to 16K context sizes. vicuna 7b v1 5 fp16 https://ollama.com/library/llama3.2-vision:90b-instruct-fp16 llama3.2-vision:90b-instruct-fp16 Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes. 2 vision 90b instruct fp16 https://ollama.com/library/gemma:7b-text-fp16 gemma:7b-text-fp16 Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1 gemma 7b text fp16 https://ollama.com/library/deepseek-r1:70b-llama-distill-fp16/blobs/81736dc6027d deepseek-r1:70b-llama-distill-fp16/model DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro. deepseek r1 70b llama distill fp16