나에게 맞는 AI 모델을 찾아보세요.

비교 추가출처 / 문서 ↗

diffusiongemma-26B-A4B-it-GGUF

unsloth

Jun 12 Update: You can now run DiffusionGemma in Unsloth Studio. See our Guide . You can also fine-tune DiffusionGemma in Unsloth . Inference settings are auto set. Example of DiffusionGemma (4-bit GGUF) running in Unsloth Studio with executable code: These GGUFs run with the DiffusionGemma build of `llama.cpp` (the DiffusionGemma PR ggml-org/llama.cpp#24423). DiffusionGemma is a block-diffusion architecture, so it needs that branch plus the dedicated `llama-diffusion-cli` runner - the standard `llama-cli` / `llama-server` cannot generate from it yet. `-n` / `--n-predict` is the only length knob you need: it auto-derives the diffusion block count and grows the batch/context to fit. On a single GPU the prompt prefix KV cache turns on automatically.

번역 대기 중 · 원문 표시

시각 질의응답

입력 텍스트 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

dots.llm1.inst-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-2

unsloth

**EmbeddingGemma 2** is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders. Designed to run on consumer hardware such as mobile devices and laptops, EmbeddingGemma 2 delivers low-latency semantic representations for on-device applications, like search, retrieval-augmented generation (RAG), classification, and clustering. EmbeddingGemma 2 builds upon the architectural and capability advancements of Gemma 4, offering several core features: 

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-2-GGUF

unsloth

Unsloth Dynamic 3.0 achieves superior accuracy & outperforms other leading quants. **EmbeddingGemma 2** is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders. Designed to run on consumer hardware such as mobile devices and laptops, EmbeddingGemma 2 delivers low-latency semantic representations for on-device applications, like search, retrieval-augmented generation (RAG), classification, and clustering.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-300m

unsloth

**Model Page**: EmbeddingGemma * Responsible Generative AI Toolkit * EmbeddingGemma on Kaggle * EmbeddingGemma on Vertex Model Garden EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-300m-GGUF

unsloth

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages. The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone. These model weights are designed to be used with Sentence Transformers, using the Gemma 3 implementation from Hugging Face Transformers as the backbone.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-300m-qat-q4_0-unquantized

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

기본 정보 등록 · 상세 정보 보완 예정

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

embeddinggemma-300m-qat-q8_0-unquantized

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

기본 정보 등록 · 상세 정보 보완 예정

입력 텍스트→ 출력 임베딩

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

ERNIE-4.5-0.3B-PT-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

ERNIE-4.5-21B-A3B-PT-GGUF

unsloth

> [!NOTE] > Note: "**-Paddle**" models use PaddlePaddle weights, while "**-PT**" models use Transformer-style PyTorch weights. The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations: 1. **Multimodal Heterogeneous MoE Pre-Training:** Our models are jointly trained on both textual and visual modalities to better capture the nuances of multimodal information and improve performance on tasks involving text understanding and generation, image understanding, and cross-modal reasoning. To achieve this without one modality hindering the learning of another, we designed a *heterogeneous MoE structure*, incorporated *modality-isolated routing*, and employed *router orthogonal loss* and *multimodal token-balanced loss*. These architectural choices ensure that both modalities are effectively represented, allowing for mutual reinforcement during training.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

ERNIE-4.5-21B-A3B-Thinking-GGUF

unsloth

Over the past three months, we have continued to scale the **thinking capability** of ERNIE-4.5-21B-A3B, improving both the **quality and depth** of reasoning, thereby advancing the competitiveness of ERNIE **lightweight models** in complex reasoning tasks. We are pleased to introduce **ERNIE-4.5-21B-A3B-Thinking**, featuring the following key enhancements: > [!NOTE] > Note: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks. ERNIE-4.5-21B-A3B-Thinking is a text MoE post-trained model, with 21B total parameters and 3B activated parameters for each token. The following are the model configuration details:

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

ERNIE-Image-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

이미지 생성

입력 텍스트→ 출력 이미지

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

ERNIE-Image-Turbo-GGUF

unsloth

This is a GGUF quantized version of ERNIE-Image-Turbo. unsloth/ERNIE-Image-Turbo-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96. ERNIE-Image-Turbo is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is the distilled release of ERNIE-Image, built on the same single-stream Diffusion Transformer (DiT) family and designed for fast generation with strong fidelity in only 8 inference steps. The model retains strong controllability in practical generation scenarios where accurate content realization matters as much as aesthetics. In particular, ERNIE-Image-Turbo remains strong on complex instruction following, text rendering, and structured image generation, making it well suited for posters, comics, multi-panel layouts, and other content creation tasks that require both visual quality and efficiency. It also supports a broad range of visual styles, including realistic photography, design-oriented imagery, and stylized aesthetic outputs. **Highlights:** - **Fast and efficient**: As the distilled checkpoint of ERNIE-Image, ERNIE-Image-Turbo delivers strong generation quality with only 8 inference steps, making it suitable for latency-sensitive applications. - **Text rendering**: ERNIE-Image-Turbo performs well on dense, long-form, and layout-sensitive text, making it a strong choice for posters, infographics, UI-like images, and other text-heavy visual content. - **Instruction following**: The model is able to follow complex prompts involving multiple objects, detailed relationships, and knowledge-intensive descriptions with strong reliability. - **Structured generation**: ERNIE-Image-Turbo is effective for structured visual tasks such as posters, comics, storyboards, and multi-panel compositions, where layout and organization are critical. - **Style coverage**: In addition to clean and readable design-oriented outputs, the model also supports realistic photography and distinctive stylized aesthetics, including softer and more cinematic visual tones. - **Practical deployment**: Thanks to its compact size, ERNIE-Image-Turbo

번역 대기 중 · 원문 표시

이미지 생성

입력 텍스트→ 출력 이미지

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-0.5B-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-1.5B-Deep-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-1.5B-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-34B-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

기본 정보 등록 · 상세 정보 보완 예정

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-3B-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1-7B-Instruct-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Falcon-H1R-7B-GGUF

unsloth

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

분류 준비 중

입력 미확인→ 출력 미확인

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

flint-GGUF

unsloth

See further below for quant benchmarks. See below for Flint running in Unsloth Desktop with thinking controls: Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests. Flint supports text input and output, reasoning, and multi-turn tool use. In our release evaluations, it scores 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2, and 74.2% on SWE-bench Verified.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인