找到适合你的 AI 模型。

加入对比来源 / 文档 ↗

Qwen3.6-35B-A3B-abliterated-v2-gguf

LMLiutenant

GGUF quantizations of wangzhang/Qwen3.6-35B-A3B-abliterated-v2, itself an abliterated (refusal-suppressed) derivative of Qwen/Qwen3.6-35B-A3B. The quantizations were made with llama.cpp. This repository is an independent redistribution and is not an official release of Qwen or of the abliteration author. The abliterated checkpoint contains the language model only. The included `mmproj-Qwen3.6-35B-A3B-F16.gguf` was converted from the vision tower of the base model `Qwen/Qwen3.6-35B-A3B`, so it is not abliterated and was not modified. Image input through this projector has not been tested for this release. To run text only, simply do not pass `--mmproj`. In llama.cpp the projector can be kept on the CPU with `--no-mmproj-offload`. The governing upstream license is the Apache License 2.0. A copy is included in `LICENSE` (identical to the copy distributed with the source checkpoint). All applicable upstream copyright, attribution and other license terms remain in effect, and this repository grants no rights beyond those provided by the upstream license. Downstream users must preserve the applicable license and attribution notices.

译文排队中 · 当前显示来源原文

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp

LMLiutenant

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。

基础资料已收录 · 缺失资料后续补充

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

Qwen3.8-Flash-Next-Uncensored-oQ6e-mtp

LMLiutenant

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。

基础资料已收录 · 缺失资料后续补充

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-OneVision-2-8B-Instruct

lmms-lab-encoder

> [!IMPORTANT] > 🌟 **The core work on this project is led by Glint Lab.** > For an interactive online experience, visit **ve2s.ai**. A multimodal vision-language model that handles **single images, multi-image, and video** inputs, built on a Qwen3-8B language backbone with a OneVision-style vision encoder. The model is distributed as a HuggingFace `transformers` checkpoint with custom code (`trust_remote_code=True`).

译文排队中 · 当前显示来源原文

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

llama3-llava-next-8b

lmms-lab

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。

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-Critic-R1-7B-Plus-Mimo

lmms-lab

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。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-Critic-R1-7B-Plus-Qwen

lmms-lab

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。

基础资料已收录 · 缺失资料后续补充

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

llava-next-72b

lmms-lab

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。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-OneVision-1.5-4B-Instruct

lmms-lab

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。

基础资料已收录 · 缺失资料后续补充

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-OneVision-1.5-8B-Instruct

lmms-lab

> [!IMPORTANT] > 🌟 **The core work on this project is led by Glint Lab.** > For an interactive online experience, visit **ve2s.ai**. LLaVA-OneVision-1.5 is a fully open-source family of large multimodal models (LMMs) built to democratize multimodal training. Trained on native‑resolution images, it delivers state‑of‑the‑art performance at substantially lower cost. The project also releases high‑quality pretraining and SFT data, a complete and efficient training framework with recipes and configs, and comprehensive logs to support transparent, reproducible research. - The model leads on multiple multimodal benchmarks and generally surpasses Qwen2.5-VL. - Training on native-resolution images significantly improves its visual understanding. Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:

译文排队中 · 当前显示来源原文

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

llava-onevision-qwen2-0.5b-ov

lmms-lab

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。

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

llava-onevision-qwen2-72b-ov-sft

lmms-lab

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。

基础资料已收录 · 缺失资料后续补充

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

llava-onevision-qwen2-7b-ov

lmms-lab

Play with the model on the LLaVA OneVision Chat. 1. Model Summary 2. Use 3. Limitations 4. Training 5. License 6. Citation The LLaVA-OneVision models are 0.5/7/72B parameter models trained on LLaVA-OneVision, based on Qwen2 language model with a context window of 32K tokens.

译文排队中 · 当前显示来源原文

输入文本→ 输出文本

价格待核验多模态与渠道费用须分别核对

加入对比来源 / 文档 ↗

LLaVA-Video-7B-Qwen2

lmms-lab

The LLaVA-Video models are 7/72B parameter models trained on LLaVA-Video-178K and LLaVA-OneVision Dataset, based on Qwen2 language model with a context window of 32K tokens. The model was trained on LLaVA-Video-178K and LLaVA-OneVision Dataset, having the ability to interact with images, multi-image and videos, but specific to videos. We provide the simple generation process for using our model. For more details, you could refer to Github.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对