From 01bddc0a109eae46be408d9d59bead3957a4c7ff Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 11 Oct 2026 17:23:19 +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/GLM-4.1V-9B-Thinking-GGUF Source: Original Platform --- .gitattributes | 46 ++++++++++++++++++++ GLM-4.1V-9B-Thinking.IQ4_XS.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q2_K.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q3_K_L.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q3_K_M.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q3_K_S.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q4_K_M.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q4_K_S.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q5_K_M.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q5_K_S.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q6_K.gguf | 3 ++ GLM-4.1V-9B-Thinking.Q8_0.gguf | 3 ++ GLM-4.1V-9B-Thinking.f16.gguf | 3 ++ README.md | 75 ++++++++++++++++++++++++++++++++ 14 files changed, 157 insertions(+) create mode 100644 .gitattributes create mode 100644 GLM-4.1V-9B-Thinking.IQ4_XS.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q2_K.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q3_K_L.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q3_K_M.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q3_K_S.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q4_K_M.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q4_K_S.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q5_K_M.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q5_K_S.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q6_K.gguf create mode 100644 GLM-4.1V-9B-Thinking.Q8_0.gguf create mode 100644 GLM-4.1V-9B-Thinking.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53de4d2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +GLM-4.1V-9B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GLM-4.1V-9B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GLM-4.1V-9B-Thinking.IQ4_XS.gguf b/GLM-4.1V-9B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..e3496c6 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5642272d0efaa036fe6d61c2776994548cae0275f8ee58200cfd5d4ae6a46d +size 5314869024 diff --git a/GLM-4.1V-9B-Thinking.Q2_K.gguf b/GLM-4.1V-9B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..8910fe7 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab6378991f6ef150a5fbc40a63ec786ea5ad54c08d57173c27ce78c53d2c763 +size 4006344480 diff --git a/GLM-4.1V-9B-Thinking.Q3_K_L.gguf b/GLM-4.1V-9B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..90ec422 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04df3f23ce4224fa2f2aa8f0cc7b77463927c1ccb262dd4f5a67915f031ba7f4 +size 5196609312 diff --git a/GLM-4.1V-9B-Thinking.Q3_K_M.gguf b/GLM-4.1V-9B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..13a7df2 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f96cd64b2d96fa24ebeb5f848ee1c91a88bb48cf1871f0eaf72bdbbb5a587f7 +size 4974507808 diff --git a/GLM-4.1V-9B-Thinking.Q3_K_S.gguf b/GLM-4.1V-9B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..a8c8018 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d211f2f8f96ab25618aeb519dffecd52ec244d85d6f9a9432634783111fb115 +size 4592039712 diff --git a/GLM-4.1V-9B-Thinking.Q4_K_M.gguf b/GLM-4.1V-9B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..d762128 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0660c4869b39a6668d5fac35fb5c62277644f00c9a59da228376c1c4f5e9af +size 6166574880 diff --git a/GLM-4.1V-9B-Thinking.Q4_K_S.gguf b/GLM-4.1V-9B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..b249663 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3817c84e98171115e5ac26d792c763ea399c24fc085f830a104ea527ce8970 +size 5758482208 diff --git a/GLM-4.1V-9B-Thinking.Q5_K_M.gguf b/GLM-4.1V-9B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..190eca7 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd9080db175935086b8c79350cc092a9bfac669b3e9a1a2f47552507ffa91b9 +size 7050917664 diff --git a/GLM-4.1V-9B-Thinking.Q5_K_S.gguf b/GLM-4.1V-9B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..639ad57 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8a17227022b2ad75654b5aab30b3e2dce99db5c247c6f87150228d2bfbab68 +size 6697514784 diff --git a/GLM-4.1V-9B-Thinking.Q6_K.gguf b/GLM-4.1V-9B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..086ab8e --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d8d3506984c06e735fbcebf7962ce3f997f3b8c7c4d413885870d857c674bbf +size 8266643232 diff --git a/GLM-4.1V-9B-Thinking.Q8_0.gguf b/GLM-4.1V-9B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..bbb5e1b --- /dev/null +++ b/GLM-4.1V-9B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8bb22a5a1d37232acc87feec483c21f01761e5af02efb4a4d23c0c51c44fa40 +size 9999611680 diff --git a/GLM-4.1V-9B-Thinking.f16.gguf b/GLM-4.1V-9B-Thinking.f16.gguf new file mode 100644 index 0000000..b46f692 --- /dev/null +++ b/GLM-4.1V-9B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a64cac06afd3446bbc5a030e840901c489b9d7f4a3f71b070d4275f0c4230f8 +size 18811582240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..22930e4 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: zai-org/GLM-4.1V-9B-Thinking +language: +- en +- zh +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zai-org/GLM-4.1V-9B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GLM-4.1V-9B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-i1-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/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q2_K.gguf) | Q2_K | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q3_K_S.gguf) | Q3_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q3_K_M.gguf) | Q3_K_M | 5.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q3_K_L.gguf) | Q3_K_L | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.IQ4_XS.gguf) | IQ4_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q4_K_S.gguf) | Q4_K_S | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q4_K_M.gguf) | Q4_K_M | 6.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q5_K_S.gguf) | Q5_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q5_K_M.gguf) | Q5_K_M | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q6_K.gguf) | Q6_K | 8.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.Q8_0.gguf) | Q8_0 | 10.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GLM-4.1V-9B-Thinking-GGUF/resolve/main/GLM-4.1V-9B-Thinking.f16.gguf) | f16 | 18.9 | 16 bpw, overkill | + +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. + +