나에게 맞는 AI 모델을 찾아보세요.

입력 텍스트 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

To run Kimi K3, use our llama.cpp PR fork or run in Unsloth Studio Full precision lossless = Q8 (UD-Q8_K_XL), which is 50GB bigger than Q4 (UD-Q4_K_XL). Has vision support! Kimi K3 has toggles for High and Max thinking in Unsloth Studio Read our Kimi K3 guide for analysis and instructions. Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning. - **New Architecture**: Kimi K3 is built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), and scales up MoE sparsity with a Stable LatentMoE framework that activates 16 out of 896 experts — yielding an approximate 2.5× improvement in overall scaling efficiency over Kimi K2. - **Long-Horizon Coding**: Operating with minimal human oversight, Kimi K3 sustains long engineering sessions, navigates massive repositories, and orchestrates terminal tools — from GPU kernel optimization and compiler development to vision-in-the-loop game dev, CAD, and even chip design. - **Agentic Knowledge Work**: Kimi K3 advances end-to-end knowledge work, producing deep research with interactive visualizations, widgets and dashboards, and motion design and video editing, powered by its native multimodal architecture. - **Native Multimodality & Long Context**: Kimi K3 understands text, images, and video within the same model, and supports a 1-million-token context window. - **Open Frontier Weights**: We release the full Kimi K3 model weights under the Kimi K3 License, making frontier intelligence openly available for research, deployment, and further innovation.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Krea-2-Raw

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 ↗

Krea-2-Turbo

unsloth

> Ungated mirror of krea/krea-2-turbo, republished by Unsloth so it > can be downloaded without a Hub gate. The weights are unmodified. See NOTICE and LICENSE > in this repo for the terms, which are the upstream terms and are unchanged. 1. Setup the official Krea 2 codebase 2. Download `turbo.safetensors` in this repo 3. `export OSS_TURBO= ` Run inference: See the full SGLang Krea 2 Cookbook here

번역 대기 중 · 원문 표시

이미지 생성

입력 텍스트→ 출력 이미지

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Krea-2-Turbo-FP8

unsloth

This is an FP8 / INT8 quantized version of Krea-2-Turbo. - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.223 INT8, 0.172 FP8. 1. Setup the official Krea 2 codebase 2. Download `turbo.safetensors` in this repo 3. `export OSS_TURBO= ` Run inference: See the full SGLang Krea 2 Cookbook here

번역 대기 중 · 원문 표시

이미지 생성

입력 텍스트→ 출력 이미지

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

Laguna-S-2.1-GGUF

unsloth

The GGUFs in this repo are Unsloth Dynamic 2.0 quants (imatrix calibrated). Laguna support is available starting from llama.cpp release b10087. Use this release or a newer one. Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention. Benchmarks as of 21 July 2026. Laguna S 2.1 in **bold**; a dash (-) marks a benchmark a model was not evaluated on. Scores marked * are as reported by third parties: Terminal-Bench 2.1 and DeepSWE via Artificial Analysis, SWE Atlas via Scale AI's official leaderboard, and Toolathlon Verified via its official leaderboard. Full evaluation trajectories: trajectories.poolside.ai.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2-1.2B

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 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2-1.2B-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 ↗

LFM2-1.2B-unsloth-bnb-4bit

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 ↗

LFM2-2.6B-Exp-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

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2-350M-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 ↗

LFM2-350M-unsloth-bnb-4bit

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 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-1.2B-Instruct

unsloth

LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. We recommend using it for agentic tasks, data extraction, and RAG. It is not recommended for knowledge-intensive tasks and programming. 1. **Function definition**: We recommend providing the list of tools as a JSON object in the system prompt. You can also use the `tokenizer.apply_chat_template()` function with tools. 2. **Function call**: By default, LFM2.5 writes Pythonic function calls (a Python list between ` ` and ` ` special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt. 3. **Function execution**: The function call is executed, and the result is returned as a "tool" role. 4. **Final answer**: LFM2 interprets the outcome of the function call to address the original user prompt in plain text.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-1.2B-Instruct-GGUF

unsloth

> [!NOTE] > Includes Unsloth **chat template fixes**! For `llama.cpp`, use `--jinja` > Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-1.2B-Thinking-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 ↗

LFM2.5-230M

unsloth

LFM2.5 is a family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. We recommend using it for data extraction and lightweight on-device agentic pipelines. It is not recommended for reasoning-heavy workloads such as advanced math, code generation, or creative writing. 1. **Function definition**: Provide the list of tools as a JSON object in the system prompt, or use `tokenizer.apply_chat_template()` with `tools=...`. 2. **Function call**: By default, LFM2.5 writes Pythonic function calls (a Python list between ` ` and ` ` special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt. 3. **Function execution**: Execute the call and return the result with the `tool` role. 4. **Final answer**: LFM2.5 interprets the tool output and returns a plain-text answer addressing the original prompt.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-230M-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 ↗

LFM2.5-24B-A2B

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 ↗

LFM2.5-24B-A2B-GGUF

unsloth

LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for **fast, private agents on-device**. It is the largest and final model in the LFM2.5 family, which now spans two orders of magnitude: from LFM2.5-230M to LFM2.5-24B-A2B. We recommend using it for agents that need to reason, call tools, and run reliably on your device. It is not recommended for knowledge-heavy tasks on its own: pair it with retrieval or web search, which plays to its tool-calling strength. > [!TIP] > 💡 **Note**: Unlike LFM2-24B-A2B, LFM2.5-24B-A2B is a pure reasoning model that always thinks before it answers. It adds a ` ` tag directly in the chat template when starting an assistant answer.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-8B-A1B

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 ↗

LFM2.5-8B-A1B-GGUF

unsloth

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning. - **On-device personal assistant**: Designed to power real-life applications, chaining tool calls, and following complex instructions on all devices. - **Compressed performance**: Competitive with much larger dense and MoE models on instruction following and agentic tasks. - **Unmatched throughput**: Fastest in its size class on both CPU and GPU inference, with day-one support for llama.cpp, MLX, vLLM, and SGLang.

번역 대기 중 · 원문 표시

입력 텍스트→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-VL-1.6B-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 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-VL-3B

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 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인

비교 추가출처 / 문서 ↗

LFM2.5-VL-3B-GGUF

unsloth

LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for **on-device deployment**. It builds on LFM2-VL-3B with further mid- and post-training. LFM2.5-VL-3B can process both text and images, and uses the LFM2.5-2.6B language model as its backbone, combined with a SigLIP2 NaFlex vision encoder. * **Better grounding**: Improved grounding and object detection with natural language queries. * **Better OCR**: Full page OCR with layout annotation. See layout annotation format for more information. * **Efficient inference**: 228 tok/s on an Apple M5 Max and 116 tok/s on an AMD Ryzen AI Max+ 395, in under 3.3 GB of memory. Find more information about LFM2.5-VL-3B in our release post.

번역 대기 중 · 원문 표시

입력 텍스트 · 이미지→ 출력 텍스트

요금 미확인멀티모달 및 채널 요금 별도 확인