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
언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.
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
> [!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
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。
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
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
**Qianfan-OCR** is a **4B-parameter end-to-end document intelligence model** developed by the Baidu Qianfan Team. It unifies document parsing, layout analysis, and document understanding within a single vision-language architecture. Unlike traditional multi-stage OCR pipelines that chain separate layout detection, text recognition, and language comprehension modules, Qianfan-OCR performs **direct image-to-Markdown conversion** and supports a broad range of prompt-driven tasks — from structured document parsing and table extraction to chart understanding, document question answering, and key information extraction — all within one model. - 🏆 **#1 End-to-End Model on OmniDocBench v1.5** — Achieves **93.12** overall score, surpassing DeepSeek-OCR-v2 (91.09), Gemini-3 Pro (90.33), and all other end-to-end models - 🏆 **#1 End-to-End Model on OlmOCR Bench** — Scores **79.8** - 🏆 **#1 on Key Information Extraction** — Overall mean score of **87.9** across five public KIE benchmarks, surpassing Gemini-3.1-Pro, Gemini-3-Pro, Seed-2.0, and Qwen3-VL-235B-A22B - 🧠 **Layout-as-Thought** — An innovative optional thinking phase that recovers explicit layout analysis within the end-to-end paradigm via `⟨think⟩` tokens - 🌍 **192 Languages** — Multilingual OCR support across diverse scripts - ⚡ **Efficient Deployment** — Achieves **1.024 PPS** (pages per second) with W8A8 quantization on a single A100 GPU
번역 대기 중 · 원문 표시
> Unlimited OCR 2 supports **Transformers** (native, for quick tests) and **SGLang** (recommended for serving). Tested with Python 3.10, `torch==2.13.0`, `transformers==4.52.1`, `huggingface-hub==0.36.0`, `tokenizers==0.21.4`, on an NVIDIA A800-80GB: **Multi-page inference** (`infer_multi`). All pages of a document are parsed in one request, so the model can use cross-page context. Pass the page images in page order:
번역 대기 중 · 원문 표시
A **`groupwise-int`** artifact of huihui-ai/Huihui-Qwen3.8-27B-abliterated, packaged for the NInfer engine. This is the refusal-removed counterpart to the official neroued/Qwen3.8-27B-NInfer artifact, using the same weights profile. One file carries the complete container — Text, Vision, MTP, the optimized proposal head, tokenizer, chat template, generation config and media-processor resources. > **There is also an NVFP4 build > of this same checkpoint.** It is ~35 % faster on speculative decode and 1.6–2× on prefill, for 3.1 GiB > more VRAM. **Prefer NVFP4 unless VRAM is tight.** This profile's advantages are a smaller footprint > (15.9 GiB resident vs 19.0) and a dramatically simpler build — one command, no external quantizer, > no calibration data, and no patch of any kind.
번역 대기 중 · 원문 표시
An **NVFP4** artifact of huihui-ai/Huihui-Qwen3.8-27B-abliterated, packaged for the NInfer engine. This is the refusal-removed (abliterated) counterpart to the official neroued/Qwen3.8-27B-NInfer artifact. It carries the complete container — Text, Vision, MTP, the optimized proposal head, tokenizer, chat template, generation config and media-processor resources — as one file. Qwen3.8-27B is the king of the local models right now, and the great work Neroued has done with the NInfer engine runs it extremely quickly on Blackwell. There has also been a lot of work on obliterating and otherwise liberating models, including Pliny's OBLITERATUS suite.
번역 대기 중 · 원문 표시
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。
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
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
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
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
AWQ **W4A16** quantization of `Qwen/Qwen3.8-27B`, produced with llm-compressor in `compressed-tensors` `pack-quantized` format — the best-optimised Marlin path on Ampere (SM 8.6). Qwen3.8-27B is a **hybrid** model. Only **16 of its 64** decoder layers use full attention; the other **48 use Gated DeltaNet** (`linear_attn.*`). Those DeltaNet projections are extremely sensitive to quantization, so they are left at full BF16 precision here, along with the vision tower and the multi-token-prediction head. That means only **256 Linear modules** are quantized — 16 layers × 4 attention projections plus 64 layers × 3 MLP projections — rather than the ~448 you would get by assuming a uniform architecture. Keeping 48 layers of DeltaNet in BF16 costs roughly 7 GB versus builds that quantize everything, and that is the entire difference in file size.
번역 대기 중 · 원문 표시
**Model details:** - Parameter count: 35B - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (22.32GB) - usually a good mix of size and performance. Download instructions available here The files marked `true` in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:
번역 대기 중 · 원문 표시
**Model details:** - Parameter count: 33B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (20.49GB) - usually a good mix of size and performance. Download instructions available here The files marked `true` in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:
번역 대기 중 · 원문 표시
**Model details:** - Parameter count: 9B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (5.21GB) - usually a good mix of size and performance. Download instructions available here These quants were made with llama.cpp release b11490 - if this model's architecture is newly supported, you'll need that release or newer to run them.
번역 대기 중 · 원문 표시
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。
**Model details:** - Parameter count: 180B (source checkpoint) - Input support: text, image (with mmproj file) - details - Speculative decoding: yes (MTP) - details - imatrix: yes - details **Don't know which to choose?** Grab Q4_K_M (127.09GB) - usually a good mix of size and performance. Download instructions available here **About these sizes:** 51.7 % of this model's weights (`per_layer_token_embd` (160 wide), `ffn_down_exps` (640 wide), `hc_attn_up` (320 wide), `hc_ffn_up` (320 wide) and 2 more) have row widths that llama.cpp's 256-wide K and IQ block types cannot use, so each size gives them one of the 32-wide types instead (Q4_0 to Q8_0, or IQ4_NL), whatever type its name asks for, and the files above are closer together in size than usual. These sizes were not made, each within 1 % of the size of another file of the same kind: Q4_K_L (0.9 % from Q5_K_S), IQ2_XXS (0.7 % from IQ2_XS).
번역 대기 중 · 원문 표시
All quants made using imatrix option with dataset from here combined with a subset of combined_all_small.parquet from Ed Addario here Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
번역 대기 중 · 원문 표시
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
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。
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
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.