From 3e4c8ce8d436ae3d28ff31b1bb4c69f99abf0649 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 28 May 2026 12:50:18 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++ Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf | 3 + Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf | 3 + README.md | 102 ++++++++++++++++++++ 27 files changed, 237 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf create mode 100644 Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d385e4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..ee85a87 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827503fcca5486545d6f18c2f6df83d556850fbafc2a6cba6b636baa28abf3f9 +size 1127020544 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..7ab5402 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a4ed9813f09bb99bc5d8959033860c5e34a6d84631a90a047ad9c327d358ea +size 1055258624 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..5da29c2 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88c1a27b0ccd0f15445bd9e420d5742a66dfb066a7edf455e9f127588613e38d +size 1512986624 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..5cf79d3 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46589f3aa449831fb310cfa800de2e594d5c9acc3ceaf71180d53983a6fa6b4 +size 1417304064 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9b89ad2 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d657a3e297ea3cdb0dcd48cf6f45828a6a51c30f1702d692d2176f889216eec +size 1354102784 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..71db83a --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f4b9c1c577354bf0d6812d9ccc212df2203b543d826f2b0b6cc1714bcf3b4d +size 1246623744 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..f712790 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b313a09af5a3effa4cc37f743cd988e158c6dbae667e88428bc5f3f52468e6f2 +size 1962898944 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..96fe1f5 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ae6fce38927295e0f6e0c84e5a3339b4c80597e6a9b27728f414b8d0f566a2 +size 1899533824 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c656575 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431c3c24e8789d2f069a0a5e7070de3cdf365ae9bac88b6da7c3290cad8a3edc +size 1814377984 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7ff5ce7 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d9c2e96d6625e4c8902626c5e0c52b6317fb967741c7e4a2ddb7f8aa6e24eb +size 1670191104 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..680616c --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46843ef2c701576afbcb6df37f917dc861a9ff8a7bf444c9107cfa572a3c1611 +size 2381346304 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1bb47a0 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26be57a3f31fa84f191a3a8f1c16f97a2c82990ae11ea867564aff3b8125997 +size 2270754304 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..81871bd --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f3a748ffe424d4f09b4a198afbe86e588133d4d1af9841addd8bfdd88670130 +size 1669502464 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3cbf761 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf6bd695a4be7521a133677f45db468a4bf83c2359e21bcc5b5cbc2edd7033c +size 1563457024 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..df78dbe --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccc30e9d04e289f0a9cc3c71fe93e9588ee715d65aa7f89b35a21ecfc1daaa5 +size 2239788544 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..92209bc --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffde21ca9854b2f2b9e30a7e7522e8de423778cd8ace972e755cb8b7480e9847 +size 2075620864 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3f26e94 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab58c0cbd43df127a7a8ba234f9ac29468adaefc72eda1111505cbd65a23dc1 +size 1887000064 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..b649c5c --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d425eef44a9ea030ab462d560ff70e5ec0f71d572726428d1f9ce8254f1ae34 +size 2375775744 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..d59468f --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293a30d449b9d92c894e6de9d08ca07d8e62cd7dafd5c32acfd1542e5ebd5c6a +size 2596632064 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0c28f7e --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97204b5c1b5ab9794ee4d9e8ae96e9fcc387239edbb174f201c37ec702cac3f +size 2497283584 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c79228f --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2b934d93e5eb3de0f5fa0aa97b747af98249c7b8f8b846c5e141174229d558 +size 2383312384 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2fce4d7 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18327d142f573f69fb86932f331ce03be4eba96d3b2a3c6c140015c3e22e9ae9 +size 2889516544 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..056eb0b --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493485fd0fd95209bf066760352c7ecc91a34ac499c6dc5ba275fd55eb17dcc6 +size 2823714304 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..14a4250 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6faca11bcf4d82e7b85b00b72383bc09f6fea16f66b9fac1e1671dfc93ee11f +size 3306264064 diff --git a/Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf b/Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf new file mode 100644 index 0000000..67fe544 --- /dev/null +++ b/Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2eaf3de8a1778414aed10e0134af6ad51c07a9950347f5cf17fd867b111c2d +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..44a66a9 --- /dev/null +++ b/README.md @@ -0,0 +1,102 @@ +--- +base_model: aifeifei798/Qwen3-VL-4B-Instruct-FT-SFT +datasets: +- TeichAI/gemini-3-pro-preview-high-reasoning-250x +- TeichAI/gemini-3-pro-preview-high-reasoning-1000x +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fragmented-training +- chain-of-thought +- reasoning +- qwen +- qwen3 +- cot +- dynamic-inference +- experimental +- sft +- unsloth +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/aifeifei798/Qwen3-VL-4B-Instruct-FT-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-GGUF).** +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Instruct-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Instruct-FT-SFT.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +