DeepSeek-V3.1-AWQ
QuantTrio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
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
Base model: google/gemma-4-31B-it This repo quantizes the model using data-free quantization (no calibration dataset required). Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on small models) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
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。
기본 정보 등록 · 상세 정보 보완 예정
Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs. The `awq_marlin` module in `vllm` misses checking the `modules_to_not_convert` parameter when loading AWQ-MoE modules, which causes mixed quantization of MoE to fail or report errors. Refer to: [[Issue #21888]](https://github.com/vllm-project/vllm/pull/21888) Before the PR is merged, temporarily replace `awq_marlin.py` in `vllm/model_executor/layers/quantization/awq_marlin.py`.
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
Base model: zai-org/GLM-4.7-Flash GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency. For local deployment, GLM-4.7-Flash supports inference frameworks including vLLM and SGLang. Comprehensive deployment instructions are available in the official Github repository.
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。
기본 정보 등록 · 상세 정보 보완 예정
Note: When launching with 8 GPUs, --enable-expert-parallel must be specified; otherwise, the expert tensors cannot be evenly split across tensor parallel ranks. This option is not required for 4-GPU setups. We introduce the updated version of the **Qwen3-235B-A22B non-thinking mode**, named **Qwen3-235B-A22B-Instruct-2507**, featuring the following key enhancements: **Qwen3-235B-A22B-Instruct-2507** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 235B in total and 22B activated - Number of Paramaters (Non-Embedding): 234B - Number of Layers: 94 - Number of Attention Heads (GQA): 64 for Q and 4 for KV - Number of Experts: 128 - Number of Activated Experts: 8 - Context Length: **262,144 natively**.
번역 대기 중 · 원문 표시
Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs. Over the past three months, we have continued to scale the **thinking capability** of Qwen3-30B-A3B, improving both the **quality and depth** of reasoning. We are pleased to introduce **Qwen3-30B-A3B-Thinking-2507**, featuring the following key enhancements: **NOTE**: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks.
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
This repo quantizes the model using data-free quantization (no calibration dataset required). > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.
번역 대기 중 · 원문 표시
> **v2 Update:** > - **Accuracy preserved:** Matches base model on HumanEval (**96.91% pass@1**) > > - **Shorter reasoning:** ~**24% reduction** in chain-of-thought length > > - **Higher efficiency:** **+31.6% more correct solutions per token** > > - ⚠️**Trade-off:** −1.24% on HumanEval+ −7.2% on MMLU-Pro (Indicating reduced general knowledge reasoning performance) > > *⚠️Note: Due to the scope of SFT data and training focus, the model may underperform the base model on certain tasks requiring long-context understanding or more complex multi-step reasoning. The efficiency and accuracy results reported here are based solely on the HumanEval and HumanEval+ benchmarks. Thank you for your understanding.* **Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2** is the second iteration of this reasoning-focused Qwen3.5-27B fine-tune, built to drastically improve the *efficiency* of chain-of-thought generation, unlocking highly substantial gains in reasoning speed and cost-reduction while actually increasing absolute accuracy. Compared with the earlier version, **v2 was trained with 14,000 Claude 4.6 Opus-style general reasoning samples**, with a stronger emphasis on transferring concise, reusable reasoning patterns rather than only maximizing raw benchmark scores. The goal of v2 is not simply to make the model "think more," but to help it **think more economically**: reducing unnecessarily long internal chains, avoiding verbose over-analysis on easy problems, and massively improving the reasoning-cost-to-quality ratio while beating the baseline's benchmark correctness.
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
This repo quantizes the model using data-free quantization (no calibration dataset required). Note: When launching with TP=8, include `--enable-expert-parallel`; otherwise the expert tensors wouldn’t be evenly sharded across GPU devices. > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
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。
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. - **Unified Vision-Language Foundation**: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
번역 대기 중 · 원문 표시
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc. Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency. - **Unified Vision-Language Foundation**: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
번역 대기 중 · 원문 표시
Base model: Qwen/Qwen3.6-27B Note: When launching with TP=8, include `--enable-expert-parallel`; otherwise the expert tensors wouldn’t be evenly sharded across GPU devices. > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
번역 대기 중 · 원문 표시
Base model: Qwen/Qwen3.6-35B-A3B Note: When launching with TP=8, include `--enable-expert-parallel`; otherwise the expert tensors wouldn’t be evenly sharded across GPU devices. > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
번역 대기 중 · 원문 표시
Base model Qwen3-Coder-30B-A3B-Instruct This model suffers from significant loss under 4-bit quantization, please use with caution. Note: You must use `--enable-expert-parallel` to start this model, otherwise the expert tensor TP will not divide evenly. This is required even for 2 GPUs.
번역 대기 중 · 원문 표시
Base model:Qwen3-Coder-30B-A3B-Instruct Note: When using 4 GPUs, you must include `--enable-expert-parallel` because expert tensor TP must be evenly divisible; for 2 GPUs this is not necessary. **Qwen3-Coder** is available in multiple sizes. Today, we're excited to introduce **Qwen3-Coder-30B-A3B-Instruct**. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements:
번역 대기 중 · 원문 표시
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.