> # Research and evaluation use only — not for commercial use > These weights are a quantized derivative of Qwen/Qwen-Image-2.1 > and are distributed under the **Qwen Research License Agreement** (LICENSE). > The license permits use, reproduction and distribution **for non-commercial purposes only**, defined as > **research or evaluation**. Any commercial use requires a separate license from the licensor > (model-business@notice.qwencloud.com). By downloading or using these files you agree to the LICENSE. An Osaurus 4bit mflux quantization of Qwen/Qwen-Image-2.1 for Apple Silicon (9.9 GB, smallest; occasional typography slips). This is not an official Qwen release and is not endorsed by the Qwen team. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
An Osaurus 6bit mflux quantization of Qwen/Qwen-Image-2.1 for Apple Silicon (14 GB, balanced size and quality). This is not an official Qwen release and is not endorsed by the Qwen team. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included. The Qwen team has stated that "Outputs are not part of the licensed Materials. Users retain the rights to images and other content they generate using the model." This does not grant commercial use of the model itself; running the model remains limited to research and evaluation unless you hold a commercial license.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
> # Research and evaluation use only — not for commercial use > These weights are a quantized derivative of Qwen/Qwen-Image-2.1 > and are distributed under the **Qwen Research License Agreement** (LICENSE). > The license permits use, reproduction and distribution **for non-commercial purposes only**, defined as > **research or evaluation**. Any commercial use requires a separate license from the licensor > (model-business@notice.qwencloud.com). By downloading or using these files you agree to the LICENSE. An Osaurus 8bit mflux quantization of Qwen/Qwen-Image-2.1 for Apple Silicon (17 GB, closest to the original; recommended). This is not an official Qwen release and is not endorsed by the Qwen team. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
An Osaurus 4-bit mflux quantization of Qwen/Qwen-Image-2.1-Turbo for Apple Silicon (9.9 GB, smallest; more composition drift between seeds). This is not an official Qwen release and is not endorsed by the Qwen team. Turbo is the 8-step distilled checkpoint of Qwen-Image-2.1. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included. Requires **Osaurus 0.25.21 or newer**. Older versions treat this bundle as Qwen-Image-2.1 and sample it on that model's 40-step schedule, which gives degraded images.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
An Osaurus 6-bit mflux quantization of Qwen/Qwen-Image-2.1-Turbo for Apple Silicon (14 GB, balanced size and quality). This is not an official Qwen release and is not endorsed by the Qwen team. Turbo is the 8-step distilled checkpoint of Qwen-Image-2.1. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included. Requires **Osaurus 0.25.21 or newer**. Older versions treat this bundle as Qwen-Image-2.1 and sample it on that model's 40-step schedule, which gives degraded images.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
An Osaurus 8-bit mflux quantization of Qwen/Qwen-Image-2.1-Turbo for Apple Silicon (17 GB, closest to the original; recommended). This is not an official Qwen release and is not endorsed by the Qwen team. Turbo is the 8-step distilled checkpoint of Qwen-Image-2.1. One bundle does both **text-to-image** and **reference editing** (up to 10 ordered reference images); the vision encoder is included. Requires **Osaurus 0.25.21 or newer**. Older versions treat this bundle as Qwen-Image-2.1 and sample it on that model's 40-step schedule, which gives degraded images.
翻訳待ち・原文を表示
入力 テキスト→ 出力 画像
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
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
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
**imatrix-calibrated GGUF builds of Raptor 0.6, a lightly tuned Spark-X2.5-4B — the format Osaurus for Windows runs.** The release write-up — what happened to Raptor 0.5, why the base changed, and how 0.6 was built and measured — is at osaurus.ai/models/raptor-06. Both quants were produced **with the importance matrix applied**. Measured against the model's own bf16 weights on a held-out corpus (100 chunks x 512 tokens) that is disjoint from the imatrix corpus — 9,166 overlapping rows were dropped and the eval asserts the result is non-empty rather than trusting the paths.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
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→ 出力 テキスト
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→ 出力 テキスト
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→ 出力 テキスト
