commit ffaf7dbf87a8cc9d86afa8c5d3fc8a9b19131a09 Author: ModelHub XC Date: Fri Oct 23 20:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Alcoft/Qwen_Qwen3-14B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c7ec44 --- /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_Qwen3-14B.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_F16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q3_K_XXL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen_Qwen3-14B_Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen_Qwen3-14B.gguf b/Qwen_Qwen3-14B.gguf new file mode 100644 index 0000000..4970677 --- /dev/null +++ b/Qwen_Qwen3-14B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd24dbf00b064cb8fbfc451a302c7cfe967e80b2e6b3b760217642097c51272 +size 29543423776 diff --git a/Qwen_Qwen3-14B_F16.gguf b/Qwen_Qwen3-14B_F16.gguf new file mode 100644 index 0000000..331e082 --- /dev/null +++ b/Qwen_Qwen3-14B_F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f894d6cf93609625d5a79245b120d82d007ff98d877c2bcc80006bbd01c88ca +size 29543423776 diff --git a/Qwen_Qwen3-14B_Q2_K.gguf b/Qwen_Qwen3-14B_Q2_K.gguf new file mode 100644 index 0000000..750b04f --- /dev/null +++ b/Qwen_Qwen3-14B_Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba1eb7e495c95251aeaeb81778aed16bbce08931499313787de63a83193f8ea +size 5753983776 diff --git a/Qwen_Qwen3-14B_Q2_K_L.gguf b/Qwen_Qwen3-14B_Q2_K_L.gguf new file mode 100644 index 0000000..1b9d125 --- /dev/null +++ b/Qwen_Qwen3-14B_Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749c6a34f9d696b357ae60f5dad58bc305aeb93d8ce58cee8ccb79e5abf5dfa6 +size 6513663776 diff --git a/Qwen_Qwen3-14B_Q2_K_XL.gguf b/Qwen_Qwen3-14B_Q2_K_XL.gguf new file mode 100644 index 0000000..f5fa5ef --- /dev/null +++ b/Qwen_Qwen3-14B_Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92890d85ef4a4166067285f861c5d026d2d2a0044fe20b61b6c8bff7f79aa4e1 +size 7972249376 diff --git a/Qwen_Qwen3-14B_Q3_K_L.gguf b/Qwen_Qwen3-14B_Q3_K_L.gguf new file mode 100644 index 0000000..53b88dc --- /dev/null +++ b/Qwen_Qwen3-14B_Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0d7f1bfc50ecf0927b55a8e66e625dea5925e94bb3cfe8ba55af333a09d330 +size 7900651296 diff --git a/Qwen_Qwen3-14B_Q3_K_M.gguf b/Qwen_Qwen3-14B_Q3_K_M.gguf new file mode 100644 index 0000000..9628bc1 --- /dev/null +++ b/Qwen_Qwen3-14B_Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5aa6ef19dea5e83d7d14b1ae5cbf753bcd67369f8983bd03b3ec995327ce0b +size 7321313056 diff --git a/Qwen_Qwen3-14B_Q3_K_S.gguf b/Qwen_Qwen3-14B_Q3_K_S.gguf new file mode 100644 index 0000000..06cbcb4 --- /dev/null +++ b/Qwen_Qwen3-14B_Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b966c83d93bac5b559e81405a74fd530aa2e3b4cc44546694874c3345bc874 +size 6657105696 diff --git a/Qwen_Qwen3-14B_Q3_K_XL.gguf b/Qwen_Qwen3-14B_Q3_K_XL.gguf new file mode 100644 index 0000000..c3d0f88 --- /dev/null +++ b/Qwen_Qwen3-14B_Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62b4c9552587a093ddb697b881bce23096e8e1e526c9ec2fea7ddd8799b14fe +size 8581324576 diff --git a/Qwen_Qwen3-14B_Q3_K_XXL.gguf b/Qwen_Qwen3-14B_Q3_K_XXL.gguf new file mode 100644 index 0000000..67f2f2e --- /dev/null +++ b/Qwen_Qwen3-14B_Q3_K_XXL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6350f5f1657ce54c048021b91f6a0dd2b360c982e37dc68828dd67e001edef1f +size 10039910176 diff --git a/Qwen_Qwen3-14B_Q4_K_L.gguf b/Qwen_Qwen3-14B_Q4_K_L.gguf new file mode 100644 index 0000000..a6d2c6d --- /dev/null +++ b/Qwen_Qwen3-14B_Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44986a06ec883cc91c01236a10929c16a52dd852f07b2206ad566fd7921f8fae +size 9579110176 diff --git a/Qwen_Qwen3-14B_Q4_K_M.gguf b/Qwen_Qwen3-14B_Q4_K_M.gguf new file mode 100644 index 0000000..6a15d16 --- /dev/null +++ b/Qwen_Qwen3-14B_Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73f34046a8ce9b72149def68e969c7819132a379c3339c762c44ec22031f204 +size 9001753376 diff --git a/Qwen_Qwen3-14B_Q4_K_S.gguf b/Qwen_Qwen3-14B_Q4_K_S.gguf new file mode 100644 index 0000000..fb61ea8 --- /dev/null +++ b/Qwen_Qwen3-14B_Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b838ceb4d9c84c90f2d4d2d398f360f73d5be0929f1c6efa6335584056de6a +size 8573475616 diff --git a/Qwen_Qwen3-14B_Q4_K_XL.gguf b/Qwen_Qwen3-14B_Q4_K_XL.gguf new file mode 100644 index 0000000..8fbba99 --- /dev/null +++ b/Qwen_Qwen3-14B_Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bda8e7102aa3cbf339150bee07162ff12fc5705382430d069590666b9683249 +size 11037695776 diff --git a/Qwen_Qwen3-14B_Q5_K_L.gguf b/Qwen_Qwen3-14B_Q5_K_L.gguf new file mode 100644 index 0000000..02a561c --- /dev/null +++ b/Qwen_Qwen3-14B_Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f01e94508dbfd15c7fcbd29afbb3be7ac38c911a8ed14ba42c4c10c27139cf +size 10994687776 diff --git a/Qwen_Qwen3-14B_Q5_K_M.gguf b/Qwen_Qwen3-14B_Q5_K_M.gguf new file mode 100644 index 0000000..5a54548 --- /dev/null +++ b/Qwen_Qwen3-14B_Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adba5ff9605b314b2a845494016c75ce31277044f4ad155366058a02473b69c8 +size 10514570016 diff --git a/Qwen_Qwen3-14B_Q5_K_S.gguf b/Qwen_Qwen3-14B_Q5_K_S.gguf new file mode 100644 index 0000000..6a289db --- /dev/null +++ b/Qwen_Qwen3-14B_Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eadcb4c70e41c1fc30c1b7f0b4772eb4ce27cd00cc6f08c9a7701444fec484ca +size 10263894816 diff --git a/Qwen_Qwen3-14B_Q5_K_XL.gguf b/Qwen_Qwen3-14B_Q5_K_XL.gguf new file mode 100644 index 0000000..cf73626 --- /dev/null +++ b/Qwen_Qwen3-14B_Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a14544842ed29b1e4aafb6c752e778fef01887133f04357b40b6541cf3f3217 +size 12453273376 diff --git a/Qwen_Qwen3-14B_Q6_K.gguf b/Qwen_Qwen3-14B_Q6_K.gguf new file mode 100644 index 0000000..34576e9 --- /dev/null +++ b/Qwen_Qwen3-14B_Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e50d573515e92b21d78ba46a0bc3105e71bb2a6bcdc1462b6b39bdea55eca5 +size 12121937696 diff --git a/Qwen_Qwen3-14B_Q6_K_L.gguf b/Qwen_Qwen3-14B_Q6_K_L.gguf new file mode 100644 index 0000000..90cf6a0 --- /dev/null +++ b/Qwen_Qwen3-14B_Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f2cb855b2d3a39aadefe6a739637b25b818db121e9c76b59d84c1fba89189b +size 12498738976 diff --git a/Qwen_Qwen3-14B_Q6_K_XL.gguf b/Qwen_Qwen3-14B_Q6_K_XL.gguf new file mode 100644 index 0000000..a4e2598 --- /dev/null +++ b/Qwen_Qwen3-14B_Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3778a9c95ecf729efce6b881afecfad9f1b822607dede05de33950496c5dfb +size 13957324576 diff --git a/Qwen_Qwen3-14B_Q8_0.gguf b/Qwen_Qwen3-14B_Q8_0.gguf new file mode 100644 index 0000000..9091367 --- /dev/null +++ b/Qwen_Qwen3-14B_Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22615017fa34741730093e6e2e35a708b824a50f0319500e22296918bb01265e +size 15698534176 diff --git a/Qwen_Qwen3-14B_Q8_K_XL.gguf b/Qwen_Qwen3-14B_Q8_K_XL.gguf new file mode 100644 index 0000000..6b5d0ad --- /dev/null +++ b/Qwen_Qwen3-14B_Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4d8c4e45dfe6fa36c05b679c8905bc8e86bf4108c98a6094bb4ef0c6e1e5fe7 +size 17157119776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1749749 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +base_model: +- Qwen/Qwen3-14B +pipeline_tag: text-generation +license: apache-2.0 +--- + +|Quant|Size|Description| +|---|---|---| +|[Q2_K](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q2_K.gguf)|5.36 GB|Not recommended for most people. Very low quality.| +|[Q2_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q2_K_L.gguf)|6.07 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q2_K_XL.gguf)|7.42 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q3_K_S.gguf)|6.2 GB|Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality.| +|[Q3_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q3_K_M.gguf)|6.82 GB|Not recommended for most people. Low quality.| +|[Q3_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q3_K_L.gguf)|7.36 GB|Not recommended for most people. Low quality.| +|[Q3_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q3_K_XL.gguf)|7.99 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q3_K_XXL.gguf)|9.35 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q4_K_S.gguf)|7.98 GB|Recommended. Slightly low quality.| +|[Q4_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q4_K_M.gguf)|8.38 GB|Recommended. Decent quality for most use cases.| +|[Q4_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q4_K_L.gguf)|8.92 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q4_K_XL.gguf)|10.28 GB|Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality.| +|[Q5_K_S](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q5_K_S.gguf)|9.56 GB|Recommended. High quality.| +|[Q5_K_M](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q5_K_M.gguf)|9.79 GB|Recommended. High quality.| +|[Q5_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q5_K_L.gguf)|10.24 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q5_K_XL.gguf)|11.6 GB|Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality.| +|[Q6_K](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q6_K.gguf)|11.29 GB|Recommended. Very high quality.| +|[Q6_K_L](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q6_K_L.gguf)|11.64 GB|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_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q6_K_XL.gguf)|13.0 GB|Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality.| +|[Q8_0](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q8_0.gguf)|14.62 GB|Recommended. Quality almost like F16.| +|[Q8_K_XL](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_Q8_K_XL.gguf)|15.98 GB|Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16.| +|[F16](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B_F16.gguf)|27.51 GB|Not recommended. Overkill. Prefer Q8_0.| +|[ORIGINAL (BF16)](https://huggingface.co/Alcoft/Qwen_Qwen3-14B-GGUF/resolve/main/Qwen_Qwen3-14B.gguf)|27.51 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/Qwen3-14B).