commit 24478b8c7185819ba2ecdb1511c701bffd41008f Author: ModelHub XC Date: Fri Oct 9 22:11:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Alcoft/Qwen_Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c04dc8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_F16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q3_K_XXL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-0.6B_Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen_Qwen3-0.6B.gguf b/Qwen_Qwen3-0.6B.gguf new file mode 100644 index 0000000..617a7f6 --- /dev/null +++ b/Qwen_Qwen3-0.6B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd1c164759a35634bb7b3be2bdfd85fd1c119405ae7ea853b9c575ddb4de52e +size 1509347488 diff --git a/Qwen_Qwen3-0.6B_F16.gguf b/Qwen_Qwen3-0.6B_F16.gguf new file mode 100644 index 0000000..32118ee --- /dev/null +++ b/Qwen_Qwen3-0.6B_F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67d81fccfdb4ec2a8aacabd9600630f59faf66893bf83e1c75e2ceef9d34b6d +size 1509347488 diff --git a/Qwen_Qwen3-0.6B_Q2_K.gguf b/Qwen_Qwen3-0.6B_Q2_K.gguf new file mode 100644 index 0000000..cfacd2e --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8517b7381751311aeb77f6f814ce6c1e0c8c5902fac12315fb6705ce019172df +size 347288736 diff --git a/Qwen_Qwen3-0.6B_Q2_K_L.gguf b/Qwen_Qwen3-0.6B_Q2_K_L.gguf new file mode 100644 index 0000000..7b48175 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a0f4cfe97d0347359fbf2aa72386e4762e779facb8f48050604e754467dd37 +size 499224736 diff --git a/Qwen_Qwen3-0.6B_Q2_K_XL.gguf b/Qwen_Qwen3-0.6B_Q2_K_XL.gguf new file mode 100644 index 0000000..944f350 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d495794da8a86d04625bedd0628df5367e446edd21d8951082881ab053f961 +size 790941856 diff --git a/Qwen_Qwen3-0.6B_Q3_K_L.gguf b/Qwen_Qwen3-0.6B_Q3_K_L.gguf new file mode 100644 index 0000000..5919863 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a49ac297bcd9409b65f204583f774449d96d02b0a117d6105691e4c48d2972de +size 435343520 diff --git a/Qwen_Qwen3-0.6B_Q3_K_M.gguf b/Qwen_Qwen3-0.6B_Q3_K_M.gguf new file mode 100644 index 0000000..d7855b4 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ad24efae82415cffdc98fdc0c2d5b1470ea4c47fbad050c5872d359fef79bb +size 413978784 diff --git a/Qwen_Qwen3-0.6B_Q3_K_S.gguf b/Qwen_Qwen3-0.6B_Q3_K_S.gguf new file mode 100644 index 0000000..54e5500 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195f50a6b92c48567272a2a44e080138c1076286bcd29c0ca2e6c61a76a9d8fd +size 389927072 diff --git a/Qwen_Qwen3-0.6B_Q3_K_XL.gguf b/Qwen_Qwen3-0.6B_Q3_K_XL.gguf new file mode 100644 index 0000000..9f82a2a --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1387745920ab2f7de90e8dc5e7544719614963c7b574a6491e93cc687391da3b +size 571478176 diff --git a/Qwen_Qwen3-0.6B_Q3_K_XXL.gguf b/Qwen_Qwen3-0.6B_Q3_K_XXL.gguf new file mode 100644 index 0000000..396980b --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q3_K_XXL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbddb0986bb66182cc67a381ad6829474b244fb6d9b1e0ebe1158b6bd48bc84 +size 863195296 diff --git a/Qwen_Qwen3-0.6B_Q4_K_L.gguf b/Qwen_Qwen3-0.6B_Q4_K_L.gguf new file mode 100644 index 0000000..0ec0b63 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e04a8664fc2a0d403cac73ec12afbe81e8b0b0f683521da8d91c682d6a4a52 +size 599691424 diff --git a/Qwen_Qwen3-0.6B_Q4_K_M.gguf b/Qwen_Qwen3-0.6B_Q4_K_M.gguf new file mode 100644 index 0000000..30e4c4e --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9f396cea37cf7795e9b77d9344a1bcb612c56d58637d2b767cb60506a9e638 +size 484220064 diff --git a/Qwen_Qwen3-0.6B_Q4_K_S.gguf b/Qwen_Qwen3-0.6B_Q4_K_S.gguf new file mode 100644 index 0000000..0cfbe64 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71378c2604e20119b14b5ada972f15a6530ac3b2e7d429437389d6ece2548be +size 470785184 diff --git a/Qwen_Qwen3-0.6B_Q4_K_XL.gguf b/Qwen_Qwen3-0.6B_Q4_K_XL.gguf new file mode 100644 index 0000000..8a19488 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f99c228e7f528effdfab5140efbc243cd1278a74986f0ba6de2ea3fbe31197 +size 891408544 diff --git a/Qwen_Qwen3-0.6B_Q5_K_L.gguf b/Qwen_Qwen3-0.6B_Q5_K_L.gguf new file mode 100644 index 0000000..5cd9040 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae36516e1ac69c5fa19c27ed2d2658255f6038c420897dadaddd02445cc47141 +size 647401632 diff --git a/Qwen_Qwen3-0.6B_Q5_K_M.gguf b/Qwen_Qwen3-0.6B_Q5_K_M.gguf new file mode 100644 index 0000000..2a81565 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee8d4aab79e90cba25c4735e8f1a8205a1dfccf1c2f9aad8dd8ede05324c6c3 +size 551378080 diff --git a/Qwen_Qwen3-0.6B_Q5_K_S.gguf b/Qwen_Qwen3-0.6B_Q5_K_S.gguf new file mode 100644 index 0000000..7db103d --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01acacaa2cbdf1d1b94a3a424f72af1f727b69e685d47ee2ee77a84ae12449c1 +size 543579296 diff --git a/Qwen_Qwen3-0.6B_Q5_K_XL.gguf b/Qwen_Qwen3-0.6B_Q5_K_XL.gguf new file mode 100644 index 0000000..ea24e3b --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8981b813e4a6e836946272745f836bc7e6fa5d1502dae647123a761f28761e7d +size 939118752 diff --git a/Qwen_Qwen3-0.6B_Q6_K.gguf b/Qwen_Qwen3-0.6B_Q6_K.gguf new file mode 100644 index 0000000..1d7d8b4 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767d26707ef4aadb3bd336c675bc3299af26a54f6eca52a17b10e0ae23a76931 +size 622733472 diff --git a/Qwen_Qwen3-0.6B_Q6_K_L.gguf b/Qwen_Qwen3-0.6B_Q6_K_L.gguf new file mode 100644 index 0000000..7fe355b --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ea48dd26aed4659d6528d0febf46ead4184927c55a1e774e318997855f40a4 +size 698093728 diff --git a/Qwen_Qwen3-0.6B_Q6_K_XL.gguf b/Qwen_Qwen3-0.6B_Q6_K_XL.gguf new file mode 100644 index 0000000..248e041 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c98c4d1146d3fa236deb2efd110aae137ed08031faf1f2f6647d7ca47de305 +size 989810848 diff --git a/Qwen_Qwen3-0.6B_Q8_0.gguf b/Qwen_Qwen3-0.6B_Q8_0.gguf new file mode 100644 index 0000000..8e33449 --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade156197bba5a2983ce2473de048b87c8e92144cf8103c4e76405ea66fd70b5 +size 804753568 diff --git a/Qwen_Qwen3-0.6B_Q8_K_XL.gguf b/Qwen_Qwen3-0.6B_Q8_K_XL.gguf new file mode 100644 index 0000000..2f1cc8d --- /dev/null +++ b/Qwen_Qwen3-0.6B_Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f6d51e78b2b835336ac702073ca5e0785e212ae97bbd575fb82527459031ef +size 1096470688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e3d13eb --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +base_model: +- Qwen/Qwen3-0.6B +pipeline_tag: text-generation +license: apache-2.0 +--- + +|Quant|Size|Description| +|---|---|---| +|[Q2_K](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K.gguf)|331.2 MB|Not recommended for most people. Very low quality.| +|[Q2_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K_L.gguf)|476.1 MB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality.| +|[Q2_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q2_K_XL.gguf)|754.3 MB|Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality.| +|[Q3_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_S.gguf)|371.86 MB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.| +|[Q3_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_M.gguf)|394.8 MB|Not recommended for most people. Low quality.| +|[Q3_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_L.gguf)|415.18 MB|Not recommended for most people. Low quality.| +|[Q3_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_XL.gguf)|545.0 MB|Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality.| +|[Q3_K_XXL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q3_K_XXL.gguf)|823.21 MB|Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality.| +|[Q4_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_S.gguf)|448.98 MB|Recommended. Slightly low quality.| +|[Q4_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_M.gguf)|461.79 MB|Recommended. Decent quality for most use cases.| +|[Q4_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_L.gguf)|571.91 MB|Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality.| +|[Q4_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q4_K_XL.gguf)|850.11 MB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.| +|[Q5_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_S.gguf)|518.4 MB|Recommended. High quality.| +|[Q5_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_M.gguf)|525.84 MB|Recommended. High quality.| +|[Q5_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_L.gguf)|617.41 MB|Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality.| +|[Q5_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q5_K_XL.gguf)|895.61 MB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.| +|[Q6_K](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K.gguf)|593.88 MB|Recommended. Very high quality.| +|[Q6_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K_L.gguf)|665.75 MB|Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality.| +|[Q6_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q6_K_XL.gguf)|943.96 MB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.| +|[Q8_0](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q8_0.gguf)|767.47 MB|Recommended. Quality almost like F16.| +|[Q8_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_Q8_K_XL.gguf)|1.02 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.| +|[F16](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B_F16.gguf)|1.41 GB|Not recommended. Overkill. Prefer Q8_0.| +|[ORIGINAL (BF16)](https://huggingface.co/Alcoft/Qwen_Qwen3-0.6B-GGUF/resolve/main/Qwen_Qwen3-0.6B.gguf)|1.41 GB|Not recommended. Overkill. Prefer Q8_0.| + +--- + +Quantized using [TAO71-AI AutoQuantizer](https://github.com/TAO71-AI/AutoQuantizer). +You can check out the original model card [here](https://huggingface.co/Qwen/Qwen3-0.6B). \ No newline at end of file