Search the full model catalog.

The 4K checkpoint of NVIDIA's 1.6B Sana model, fine-tuned from the 1024px BF16 release to generate images up to 4096 × 4096, with prompts in English, Chinese or emoji.

NVIDIA's 1.6B-parameter Sana text-to-image model in BF16, built for 1024px images. It accepts English, Chinese and emoji prompts, and the 2K and 4K Sana checkpoints were fine-tuned from it.

The largest Qwen-based R1 distill, built by DeepSeek on Qwen2.5-32B. DeepSeek's results put it ahead of OpenAI o1-mini on AIME 2024, MATH-500, GPQA Diamond and LiveCodeBench.

The mid-sized R1 distill: Qwen2.5-14B fine-tuned on DeepSeek-R1 samples. DeepSeek reports results close to or above OpenAI o1-mini on most of the benchmarks it lists.

DeepSeek's R1 distill on a Llama 3.1 8B base. It writes out a chain of thought before answering and is the only Llama option among the smaller R1 distills.

Qwen2.5-Math-7B fine-tuned by DeepSeek on samples from DeepSeek-R1. A 7B model that shows its working on math problems; DeepSeek reports 92.8 on MATH-500, above OpenAI o1-mini.

DeepSeek's smallest R1 distill: Qwen2.5-Math-1.5B fine-tuned on samples generated by DeepSeek-R1. It works through a math problem step by step before it gives the answer.

Matches uploaded CVs to a comma-separated list of required skills and returns a SkillMatchScore per candidate, with the parsed profile as an option.

A 9B-parameter model from the EU-funded EuroLLM project, instruction-tuned for chat and translation in all 24 official EU languages plus 11 others, among them Turkish and Arabic.

The first instruction-tuned model in the EU-funded EuroLLM series: 1.7B parameters, tuned on EuroBlocks for translation and general instructions in 35 languages, including all 24 official EU languages.

A 3.21B-parameter Llama 3.2 model that Meta distilled from Llama 3.1 8B and 70B, for multilingual chat and summarization. On Wiro it takes up to 128 function tools and can reply with a JSON object.

Code Llama 34B Instruct is Meta's 34-billion-parameter code model tuned to follow chat instructions. Meta groups the 34B with the 70B as the sizes that return its best results.

The 7B instruction-tuned Code Llama from Meta writes and explains code from plain-English requests. It is the smallest Instruct size in the family.

A Wiro app that runs NVIDIA's 1.6B Sana text-to-image model with a base model picker, switching between four checkpoints that target 1024px, 2K and 4K output.

The 8-billion-parameter instruction model of InternLM3, from Shanghai AI Laboratory. It replies directly in normal mode or works through a long chain of thought in deep thinking mode.

Cohere Labs' open-weight 8B chat model, tuned for 23 languages including Arabic, Hindi, Persian and Vietnamese. The weights are under a non-commercial CC-BY-NC license.

A 12B model that Mistral AI trained jointly with NVIDIA, instruction-tuned for chat in many languages and for function calling. The card calls it a drop-in replacement for Mistral 7B.

A math and science model built on Mistral 7B for problems that take several steps of reasoning. Mistral AI reports 56.6% on the MATH benchmark for it.

A 7B math model from DeepSeek, instruction-tuned on 776K English and Chinese examples. It writes step-by-step solutions and, with the recommended prompt, puts the final answer in \boxed{}.

A 3.8B-parameter Phi-3.5 chat model from Microsoft, post-trained for multi-turn and multilingual conversation across 23 listed languages. Released under the MIT license.