Qwen3.6-27B-UD-MLX-MXFP4
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。
基本情報を収録・詳細は順次追加
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗DISCOVER & COMPARE
AIモデルを探す 1038
Qwen3.6-27B-UD-MLX-NVFP4
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。
基本情報を収録・詳細は順次追加
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B
unsloth> [!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. Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. For streamlined integration, we recommend using Qwen3.6 via APIs. Below is a guide to use Qwen3.6 via OpenAI-compatible API.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-GGUF
unslothNEW: Developer Role Support so Qwen3.6 can work in Codex, OpenCode and more! Qwen3.6 can now be run and fine-tuned in Unsloth Studio . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. Example of Qwen3.6 (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!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. Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-MLX-8bit
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。
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-MTP-GGUF
unslothMTP enables ~1.5-2x faster inference with no accuracy loss. You can now run Qwen3.6 MTP GGUFs in Unsloth Studio Unsloth Studio auto sets the ideal MTP settings for your hardware (Mac, CPU, GPU): Set `-DGGML_CUDA=OFF` for CPU/Metal. `-np > 1` and `--mmproj` are not yet supported with MTP. --- - Developer Role Support so Qwen3.6 can work in Codex , OpenCode and more! - Qwen3.6 can now be run and fine-tuned in Unsloth Studio . Read our guide . - Tool calling improvements: Makes parsing nested objects to make tool calling succeed more.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-NVFP4
unsloth* **1.56x faster** throughput than other NVFP4 quants. * This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. * Works on a 32GB VRAM GPU. Benchmarks on 1xB200 128 concurrency. * Use the 35B NVFP4 Fast version for **1.79x faster** at a little less accuracy For accuracy benchmarks, we conducted MMLU-Pro, AIME 2025, GPQA for FP8, BF16, NVIDIA's NVFP4 and our NVFP4s - we show our faster quants do similarly on all: Read all benchmarks in our NVFP4 blog
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-NVFP4-Fast
unsloth* **1.79x faster** throughput than other NVFP4 quants. * This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. * Works on a 32GB VRAM GPU. Benchmarks on 1xB200 128 concurrency. For accuracy benchmarks, we conducted MMLU-Pro, AIME 2025, GPQA for FP8, BF16, NVIDIA's NVFP4 and our NVFP4s - we show our faster quants do similarly on all: Read all benchmarks in our NVFP4 blog
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-UD-MLX-3bit
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。
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.6-35B-A3B-UD-MLX-4bit
unslothNEW: Developer Role Support so Qwen3.6 can work in Codex, OpenCode and more! Qwen3.6 can now be run and fine-tuned in Unsloth Studio . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. Example of Qwen3.6 (4-bit GGUF) running in Unsloth Studio with tool-calling: > [!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. Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-2.4T-A95B-GGUF
unslothSee our Qwen3.8 guide for quantization analysis and instructions. You can now run Qwen3.8 in Unsloth Desktop with toggles for thinking. New sub IQ1_S data-types Q1_0 (IQ1_XXXXS) for Qwen 3.8 See below for 1-bit Qwen3.8 run inside of Unsloth: > [!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 vLLM, SGLang, TokenSpeed, etc. > [!Tip] > For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. > > In particular, **Qwen3.8-Max** is the official version based on Qwen3.8-2.4T-A95B with more features, such as vision input & non-thinking support, 1M context length by default, official built-in tools, etc. > For more information, please refer to the Qwen3.8-Max Overview.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-27B
unslothDeveloper Role Support so Qwen3.8 can work in agentic tools like Codex and more! Qwen3.8 can now be run and fine-tuned in Unsloth Desktop . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. See below for 1-bit Qwen3.8 run inside of Unsloth: Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.
翻訳待ち・原文を表示
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-27B-FP8
unsloth> [!Note] > This repository contains FP8-quantized 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, TokenSpeed, etc. > > The quantization method is fine-grained fp8 quantization with block size of 128, and its performance metrics are nearly identical to those of the original model. > [!Tip] > For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. > > In particular, **Qwen3.8-27B** will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates. Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
翻訳待ち・原文を表示
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-27B-GGUF
unslothIntroducing Dynamic V3.0 GGUFs for SOTA accuracy and quantization performance Run and fine-tune Qwen3.8 in Unsloth Desktop with Thinking toggles . Download for Mac, Windows and Linux. GitHub repo Developer Role Support so Qwen3.8 can work in agentic tools like Codex and more! Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. See below for 4-bit Qwen3.8-27B run inside of Unsloth Desktop: Analysis of best Qwen3.8 GGUF providers. Unsloth Dynamic v3.0 delivers >10% top-1% better accuracy at the same size compared to every other provider. Read more Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-27B-NVFP4
unsloth> [!Note] > This model works with vLLM. It also works with SGLang, but only with the v0.5.19, because the `lm_head` is FP8 rather than 4-bit. This NVFP4 quant uses Unsloth Dynamic V3.0 (preview) for SOTA quantization performance. Developer Role Support so Qwen3.8 can work in agentic tools like Codex and more! MTP for fast inference is available. Qwen3.8 can now be run and fine-tuned in Unsloth Desktop . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. See below for 4-bit Qwen3.8-27B run inside of Unsloth Desktop:
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-27B-unsloth-bnb-4bit
unslothDeveloper Role Support so Qwen3.8 can work in agentic tools like Codex and more! Qwen3.8 can now be run and fine-tuned in Unsloth Desktop . Read our guide . Tool calling improvements: Makes parsing nested objects to make tool calling succeed more. See below for 1-bit Qwen3.8 run inside of Unsloth: Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.
翻訳待ち・原文を表示
入力 未確認→ 出力 未確認
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-Flash-Next
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。
基本情報を収録・詳細は順次追加
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-Flash-Next-FP8
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。
入力 テキスト · 画像→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3.8-Flash-Next-GGUF
unslothUnsloth Dynamic 3.0 achieves superior accuracy & outperforms other leading quants. MTP is now available for 1.3-1.7x Faster inference in Unsloth. Read Guide To run, please use llama.cpp or use our Unsloth Desktop app. See below for Qwen3.8-Flash-Next run in Unsloth Desktop with thinking controls: As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so. Sustainable progress toward artificial general intelligence (AGI) that benefits everyone demands architectural innovation. Today, we are sharing a concrete step in that direction: Qwen3.8-Flash-Next.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3-8B
unslothQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios. - **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning. - **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience. - **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks. - **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**. **Qwen3-8B** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 8.2B - Number of Paramaters (Non-Embedding): 6.95B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 32,768 natively and 131,072 tokens with YaRN.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3-8B-128K-GGUF
unslothQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: **Qwen3-8B** has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Number of Parameters: 8.2B - Number of Paramaters (Non-Embedding): 6.95B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 32,768 natively and 131,072 tokens with YaRN. For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3-8B-Base
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。
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3-8B-Base-bnb-4bit
unslothQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: **Qwen3-8B-Base** has the following features: - Type: Causal Language Models - Training Stage: Pretraining - Number of Parameters: 8.2B - Number of Paramaters (Non-Embedding): 6.95B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 32,768 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: **Qwen3-8B-Base** has the following features: - Type: Causal Language Models - Training Stage: Pretraining - Number of Parameters: 8.2B - Number of Paramaters (Non-Embedding): 6.95B - Number of Layers: 36 - Number of Attention Heads (GQA): 32 for Q and 8 for KV - Context Length: 32,768 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
料金未確認マルチモーダル・チャネル料金は個別に確認
詳細を見る ↗該当するモデルがありません
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
COST EXPLORER
モデル選びに、費用の視点も。
月間トークン数を調整してAPI費用を比較。
1 M = 100万トークン・米ドル
同一チャネルの基本テキスト料金を比較
同一チャネルの基本テキスト料金を比較
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
MODEL HANDBOOK
モデルを理解して選ぶ
API料金はどう比較しますか？+
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
オープンウェイトは無料で商用利用できますか？+
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
ランキング1位が最適ですか？+
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。