Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
README (all 7 languages): models in the order Qwen3.8-Flash-Next, Qwen3.6-35B-A3B, DeepSeek V4.1-Flash
Niko122141cf05a06a25
diff --git a/README.de.md b/README.de.mdindex 006a8a3bc..070c03f3c 100644--- a/README.de.md+++ b/README.de.md@@ -28,6 +28,29 @@Wir empfehlen **zuerst ISTA-DASLab**, danach **Unsloth** und andere Anbieter, soweit ein passendes Modell in deinen Speicher passt.+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| Anbieter | Auswahl |+| --- | --- |+| **ISTA-DASLab · empfohlen** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) zum Programmieren. |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Geringerer Speicherbedarf, aber langsamer. |+| **Weitere Optionen** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[Größen, Speicherbedarf und Kompatibilität vergleichen](docs/MODELS.md).++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Das sind die derzeit dokumentierten Pakete für dieses Modell.++[Modellanleitung und Kompatibilität](docs/QWEN36.md).++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ Gemessen mit dem 2.00-bpw-Set auf Strata 0.2.5. „Ausgabe“ ist das Tempo der</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| Anbieter | Auswahl |-| --- | --- |-| **ISTA-DASLab · empfohlen** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) zum Programmieren. |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Geringerer Speicherbedarf, aber langsamer. |-| **Weitere Optionen** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[Größen, Speicherbedarf und Kompatibilität vergleichen](docs/MODELS.md).--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Das sind die derzeit dokumentierten Pakete für dieses Modell.--[Modellanleitung und Kompatibilität](docs/QWEN36.md).--</details>-<a id="the-other-sizes"></a>Unsicher, was passt? [Wähle ein Modell für deinen Computer](docs/MODELS.md#pick-by-memory).diff --git a/README.es.md b/README.es.mdindex 202480b25..e9efd7234 100644--- a/README.es.md+++ b/README.es.md@@ -28,6 +28,29 @@Recomendamos **primero ISTA-DASLab**, después **Unsloth** y otros proveedores, siempre que haya un modelo compatible que quepa en tu memoria.+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| Proveedor | Opciones |+| --- | --- |+| **ISTA-DASLab · recomendado** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) para programar. |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Usa menos memoria, pero es más lento. |+| **Otras opciones** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[Compara tamaños, necesidades de memoria y compatibilidad](docs/MODELS.md).++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Son los paquetes documentados actualmente para este modelo.++[Guía del modelo y compatibilidad](docs/QWEN36.md).++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ Medido con el conjunto de 2.00 bpw en Strata 0.2.5. «Salida» es la velocidad d</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| Proveedor | Opciones |-| --- | --- |-| **ISTA-DASLab · recomendado** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) para programar. |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Usa menos memoria, pero es más lento. |-| **Otras opciones** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[Compara tamaños, necesidades de memoria y compatibilidad](docs/MODELS.md).--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Son los paquetes documentados actualmente para este modelo.--[Guía del modelo y compatibilidad](docs/QWEN36.md).--</details>-<a id="the-other-sizes"></a>¿No sabes qué cabe? [Elige un modelo para tu ordenador](docs/MODELS.md#pick-by-memory).diff --git a/README.fr.md b/README.fr.mdindex e1f9e6a0a..eb4e67234 100644--- a/README.fr.md+++ b/README.fr.md@@ -28,6 +28,29 @@Nous recommandons **d'abord ISTA-DASLab**, puis **Unsloth** et d'autres fournisseurs, lorsqu'un modèle compatible tient en mémoire.+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| Fournisseur | Choix |+| --- | --- |+| **ISTA-DASLab · recommandé** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder : IQ1\_M](docs/MODELS.md#coder) pour programmer. |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Utilise moins de mémoire, mais plus lent. |+| **Autres options** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[Comparer les tailles, la mémoire nécessaire et la compatibilité](docs/MODELS.md).++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Ce sont les paquets actuellement documentés pour ce modèle.++[Guide du modèle et compatibilité](docs/QWEN36.md).++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ Mesuré avec le jeu 2.00 bpw sur Strata 0.2.5. « Sortie » est la vitesse de la</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| Fournisseur | Choix |-| --- | --- |-| **ISTA-DASLab · recommandé** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder : IQ1\_M](docs/MODELS.md#coder) pour programmer. |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Utilise moins de mémoire, mais plus lent. |-| **Autres options** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[Comparer les tailles, la mémoire nécessaire et la compatibilité](docs/MODELS.md).--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Ce sont les paquets actuellement documentés pour ce modèle.--[Guide du modèle et compatibilité](docs/QWEN36.md).--</details>-<a id="the-other-sizes"></a>Vous ne savez pas ce qui tient ? [Choisir un modèle pour votre ordinateur](docs/MODELS.md#pick-by-memory).diff --git a/README.ja.md b/README.ja.mdindex f821df1d8..4a1800769 100644--- a/README.ja.md+++ b/README.ja.md@@ -28,6 +28,29 @@まず **ISTA-DASLab** をおすすめします。次に **Unsloth** などの提供元です。メモリに収まる互換モデルがある場合に選べます。+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| 提供元 | 選択肢 |+| --- | --- |+| **ISTA-DASLab · おすすめ** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S。[Coder: IQ1\_M](docs/MODELS.md#coder)(コーディング向け)。 |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)。メモリ使用量は少ないですが、動作は遅くなります。 |+| **その他の選択肢** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[サイズ、必要なメモリ、互換性を比べる](docs/MODELS.md)。++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0。現在、このモデルで文書化されているパックです。++[モデルガイドと互換性](docs/QWEN36.md)。++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ Strata 0.2.5 で 2.00 bpw のセットを使って測定しました。「出力</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| 提供元 | 選択肢 |-| --- | --- |-| **ISTA-DASLab · おすすめ** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S。[Coder: IQ1\_M](docs/MODELS.md#coder)(コーディング向け)。 |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)。メモリ使用量は少ないですが、動作は遅くなります。 |-| **その他の選択肢** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[サイズ、必要なメモリ、互換性を比べる](docs/MODELS.md)。--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0。現在、このモデルで文書化されているパックです。--[モデルガイドと互換性](docs/QWEN36.md)。--</details>-<a id="the-other-sizes"></a>どれが動くかわからない場合は、[お使いのパソコンに合うモデルを選ぶ](docs/MODELS.md#pick-by-memory)。diff --git a/README.md b/README.mdindex bab4703a6..0c9be0d15 100644--- a/README.md+++ b/README.md@@ -28,6 +28,29 @@We recommend **ISTA-DASLab first**, then **Unsloth** and other providers, where a compatible model fits.+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| Provider | Choices |+| --- | --- |+| **ISTA-DASLab · recommended** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) for coding. |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Lower memory use but slower. |+| **Other options** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[Compare sizes, memory needs and compatibility](docs/MODELS.md).++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. These are the currently documented packs for this model.++[Model guide and compatibility](docs/QWEN36.md).++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -60,29 +83,6 @@ Measured with the 2.00 bpw set on Strata 0.2.5. Output is the speed of the answe</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| Provider | Choices |-| --- | --- |-| **ISTA-DASLab · recommended** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) for coding. |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Lower memory use but slower. |-| **Other options** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[Compare sizes, memory needs and compatibility](docs/MODELS.md).--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. These are the currently documented packs for this model.--[Model guide and compatibility](docs/QWEN36.md).--</details>-<a id="the-other-sizes"></a>Not sure what fits? [Choose a model for your computer](docs/MODELS.md#pick-by-memory).diff --git a/README.pt-BR.md b/README.pt-BR.mdindex 7a50e91c3..f268b29a3 100644--- a/README.pt-BR.md+++ b/README.pt-BR.md@@ -28,6 +28,29 @@Recomendamos **primeiro a ISTA-DASLab**, depois a **Unsloth** e outros provedores, quando um modelo compatível cabe na memória.+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| Provedor | Opções |+| --- | --- |+| **ISTA-DASLab · recomendado** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) para programar. |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Usa menos memória, mas é mais lento. |+| **Outras opções** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[Compare tamanhos, necessidades de memória e compatibilidade](docs/MODELS.md).++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Esses são os pacotes documentados atualmente para este modelo.++[Guia do modelo e compatibilidade](docs/QWEN36.md).++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ Medido com o conjunto de 2.00 bpw no Strata 0.2.5. “Saída” é a velocidade</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| Provedor | Opções |-| --- | --- |-| **ISTA-DASLab · recomendado** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S. [Coder: IQ1\_M](docs/MODELS.md#coder) para programar. |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF). Usa menos memória, mas é mais lento. |-| **Outras opções** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[Compare tamanhos, necessidades de memória e compatibilidade](docs/MODELS.md).--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0. Esses são os pacotes documentados atualmente para este modelo.--[Guia do modelo e compatibilidade](docs/QWEN36.md).--</details>-<a id="the-other-sizes"></a>Não sabe o que cabe? [Escolha um modelo para o seu computador](docs/MODELS.md#pick-by-memory).diff --git a/README.zh-CN.md b/README.zh-CN.mdindex d1973037b..43abda7b7 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -28,6 +28,29 @@我们**首先推荐 ISTA-DASLab**,其次是 **Unsloth** 和其他提供方,前提是有内存放得下的兼容模型。+<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>++| 提供方 | 可选项 |+| --- | --- |+| **ISTA-DASLab · 推荐** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S。[Coder:IQ1\_M](docs/MODELS.md#coder),适合写代码。 |+| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |+| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)。占用内存更少,但速度更慢。 |+| **其他选项** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |++[比较大小、内存需求和兼容性](docs/MODELS.md)。++</details>++<details>+<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>++**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0。这些是目前文档中收录的该模型的版本。++[模型指南和兼容性](docs/QWEN36.md)。++</details>+<details><summary><img src="docs/media/models/deepseek.svg" width="22" alt="" align="middle"> <b>DeepSeekV4.1-Flash-1017</b></summary>@@ -58,29 +81,6 @@ strata launch --family deepseek41 --model ist-das-2.00bpw --plan</details>-<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.8-Flash-Next</b></summary>--| 提供方 | 可选项 |-| --- | --- |-| **ISTA-DASLab · 推荐** | Q2\_0, IQ2\_XS, IQ3\_XXS, IQ3\_S。[Coder:IQ1\_M](docs/MODELS.md#coder),适合写代码。 |-| **Unsloth** | UD-IQ4\_XS, UD-Q4\_K\_XL, UD-Q5\_K\_XL, UD-Q6\_K\_XL, Q8\_0 |-| **Gyro · agentionai** | [Gyro-S, Gyro-M](https://huggingface.co/agentionai/Qwen3.8-Flash-Next-Gyro-GGUF)。占用内存更少,但速度更慢。 |-| **其他选项** | [Swift 1.5](docs/MODELS.md#swift-15), [NVFP4](docs/NVFP4.md), [OrcaRouter](docs/ORCA.md) |--[比较大小、内存需求和兼容性](docs/MODELS.md)。--</details>--<details>-<summary><img src="docs/media/models/qwen.svg" width="22" alt="" align="middle"> <b>Qwen3.6-35B-A3B</b></summary>--**Unsloth:** UD-Q4_K_XL, UD-Q6_K_XL, Q8_0。这些是目前文档中收录的该模型的版本。--[模型指南和兼容性](docs/QWEN36.md)。--</details>-<a id="the-other-sizes"></a>不确定哪个放得下?[为你的电脑选择模型](docs/MODELS.md#pick-by-memory)。