From a9c1bfad49a0858bde816b712f09cd77d25f6e75 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 14 Aug 2026 10:05:12 +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: prithivMLmods/jupyter-agent-qwen3-4b-AIO-GGUF Source: Original Platform --- jupyter-agent-qwen3-4b-instruct.BF16.gguf | 3 + jupyter-agent-qwen3-4b-instruct.F16.gguf | 3 + jupyter-agent-qwen3-4b-instruct.F32.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q2_K.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q6_K.gguf | 3 + jupyter-agent-qwen3-4b-instruct.Q8_0.gguf | 3 + .gitattributes | 74 +++++++++++++++++++ README.md | 74 +++++++++++++++++++ config.json | 3 + configuration.json | 1 + ... jupyter-agent-qwen3-4b-thinking.BF16.gguf | 3 + .../ jupyter-agent-qwen3-4b-thinking.F16.gguf | 3 + .../ jupyter-agent-qwen3-4b-thinking.F32.gguf | 3 + ... jupyter-agent-qwen3-4b-thinking.Q2_K.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q3_K_L.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q3_K_M.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q3_K_S.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q4_K_M.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q4_K_S.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q5_K_M.gguf | 3 + ...upyter-agent-qwen3-4b-thinking.Q5_K_S.gguf | 3 + ... jupyter-agent-qwen3-4b-thinking.Q6_K.gguf | 3 + ... jupyter-agent-qwen3-4b-thinking.Q8_0.gguf | 3 + 30 files changed, 230 insertions(+) create mode 100644 jupyter-agent-qwen3-4b-instruct.BF16.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.F16.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.F32.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q2_K.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q6_K.gguf create mode 100644 jupyter-agent-qwen3-4b-instruct.Q8_0.gguf create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.BF16.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F16.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F32.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q2_K.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q6_K.gguf create mode 100644 jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q8_0.gguf diff --git a/ jupyter-agent-qwen3-4b-instruct.BF16.gguf b/ jupyter-agent-qwen3-4b-instruct.BF16.gguf new file mode 100644 index 0000000..a9881e2 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6dda33580d179efbf45cc1841f85c0c31497582f455367febabfe697b6cb4d +size 8051284800 diff --git a/ jupyter-agent-qwen3-4b-instruct.F16.gguf b/ jupyter-agent-qwen3-4b-instruct.F16.gguf new file mode 100644 index 0000000..bed5c54 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30938abcc03e5106cba2107df14754fc4948a3914ba962ec92f31afa0c74dd57 +size 8051284800 diff --git a/ jupyter-agent-qwen3-4b-instruct.F32.gguf b/ jupyter-agent-qwen3-4b-instruct.F32.gguf new file mode 100644 index 0000000..3ca9b7f --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95bc38db283df6cb6583faf41574ef92e0c515203b63f0af2a7e681cbe6c833 +size 16095828800 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q2_K.gguf b/ jupyter-agent-qwen3-4b-instruct.Q2_K.gguf new file mode 100644 index 0000000..2368780 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2f3d775dbc53e9deceebc54c1fb50b4c2d5e59d79d5ad08506168c602aa3a3 +size 1669499200 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf b/ jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..74a29b6 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cbcde3fba49f5f59bc3eed762575f75dc91cbfb74378fa61fd2ecd5ddd355cb +size 2239785280 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf b/ jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..84d130c --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1742bad6ea4f3d39729efcf45a8b32504e061856d6f8ed545a27d8a5f3c15db8 +size 2075617600 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf b/ jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..196b8ee --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2742b4fff82044eace4b8393d0e6c51722c0ead514f794d03b071ca773137b +size 1886996800 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf b/ jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c36ee88 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e88a0eafdf75b8b8e9ae4ab164e50e677a7580cfe46f38860baabe3364d4b3 +size 2497280320 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf b/ jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..73be0f5 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85b29a3f7202a4b5f778b3b2d6e38f30d2c63d3c4b1b0a3b23220fedb5be33e +size 2383309120 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf b/ jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7ac72b0 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f862f79d7ad0049ac07c3d8288cc4bd0ef47b0d07b194da711509dabd1bbce43 +size 2889513280 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf b/ jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..ff84287 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a79bce9dab0e57a6305c77a5fb39391d39c567d8b624a24b44f23ec7c58300 +size 2823711040 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q6_K.gguf b/ jupyter-agent-qwen3-4b-instruct.Q6_K.gguf new file mode 100644 index 0000000..856ef62 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4533ec98581a77a5e1a6b8d5d4a9b7f97355033709ecc095c3eaf001ad2baa9 +size 3306260800 diff --git a/ jupyter-agent-qwen3-4b-instruct.Q8_0.gguf b/ jupyter-agent-qwen3-4b-instruct.Q8_0.gguf new file mode 100644 index 0000000..f543004 --- /dev/null +++ b/ jupyter-agent-qwen3-4b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32cc5e33ac06d230a37bcdb9cb77c02a9d6fd5909ba7496bc1358691dc5d6e1d +size 4280404800 diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ae3f62 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,74 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + + jupyter-agent-qwen3-4b-instruct.BF16.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.F32.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F32.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.BF16.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text + jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F16.gguf filter=lfs diff=lfs merge=lfs -text +jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..e7c6dc0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +license: apache-2.0 +base_model: +- jupyter-agent/jupyter-agent-qwen3-4b-thinking +- jupyter-agent/jupyter-agent-qwen3-4b-instruct +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- jupyter-agent +- text-generation-inference +- kaggle +- agent +- code +datasets: +- jupyter-agent/jupyter-agent-dataset +--- + +# **jupyter-agent-qwen3-4b-AIO-GGUF** + +> [Jupyter-agent-qwen3-4b-instruct and jupyter-agent-qwen3-4b-thinking](https://huggingface.co/collections/jupyter-agent/jupyter-agent-68c18c9139c6ba3310ed6067) are specialized 4B-parameter models built on Qwen3-4B for agentic reasoning and data science tasks in Jupyter notebooks, supporting both general instruction following and step-by-step, notebook-native logical analysis. The instruct variant excels at delivering fast, efficient responses without generating detailed reasoning traces, while the thinking variant provides comprehensive intermediate computations and analysis, including tool calling and dataset-grounded reasoning on realistic Kaggle workflows, making both models state-of-the-art for code execution, data exploration, and practical problem solving in Python and multi-turn notebook environments. + +| Model Name | Download Link | +|------------------------------------------|-----------------------------------------------------------------------------------------------| +| **jupyter-agent-qwen3-4b-instruct-GGUF** | [Link](https://huggingface.co/prithivMLmods/jupyter-agent-qwen3-4b-AIO-GGUF/tree/main) | +| **jupyter-agent-qwen3-4b-thinking-GGUF** | [Link](https://huggingface.co/prithivMLmods/jupyter-agent-qwen3-4b-AIO-GGUF/tree/main/jupyter-agent-qwen3-4b-thinking) | + +## Model Files + +### jupyter-agent-qwen3-4b-instruct-GGUF + +| File Name | Quant Type | File Size | +| - | - | - | +| jupyter-agent-qwen3-4b-instruct.BF16.gguf | BF16 | 8.05 GB | +| jupyter-agent-qwen3-4b-instruct.F16.gguf | F16 | 8.05 GB | +| jupyter-agent-qwen3-4b-instruct.F32.gguf | F32 | 16.1 GB | +| jupyter-agent-qwen3-4b-instruct.Q2_K.gguf | Q2_K | 1.67 GB | +| jupyter-agent-qwen3-4b-instruct.Q3_K_L.gguf | Q3_K_L | 2.24 GB | +| jupyter-agent-qwen3-4b-instruct.Q3_K_M.gguf | Q3_K_M | 2.08 GB | +| jupyter-agent-qwen3-4b-instruct.Q3_K_S.gguf | Q3_K_S | 1.89 GB | +| jupyter-agent-qwen3-4b-instruct.Q4_K_M.gguf | Q4_K_M | 2.5 GB | +| jupyter-agent-qwen3-4b-instruct.Q4_K_S.gguf | Q4_K_S | 2.38 GB | +| jupyter-agent-qwen3-4b-instruct.Q5_K_M.gguf | Q5_K_M | 2.89 GB | +| jupyter-agent-qwen3-4b-instruct.Q5_K_S.gguf | Q5_K_S | 2.82 GB | +| jupyter-agent-qwen3-4b-instruct.Q6_K.gguf | Q6_K | 3.31 GB | +| jupyter-agent-qwen3-4b-instruct.Q8_0.gguf | Q8_0 | 4.28 GB | + +### jupyter-agent-qwen3-4b-thinking-GGUF + +| File Name | Quant Type | File Size | +| - | - | - | +| jupyter-agent-qwen3-4b-thinking.BF16.gguf | BF16 | 8.05 GB | +| jupyter-agent-qwen3-4b-thinking.F16.gguf | F16 | 8.05 GB | +| jupyter-agent-qwen3-4b-thinking.F32.gguf | F32 | 16.1 GB | +| jupyter-agent-qwen3-4b-thinking.Q2_K.gguf | Q2_K | 1.67 GB | +| jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf | Q3_K_L | 2.24 GB | +| jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf | Q3_K_M | 2.08 GB | +| jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf | Q3_K_S | 1.89 GB | +| jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf | Q4_K_M | 2.5 GB | +| jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf | Q4_K_S | 2.38 GB | +| jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf | Q5_K_M | 2.89 GB | +| jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf | Q5_K_S | 2.82 GB | +| jupyter-agent-qwen3-4b-thinking.Q6_K.gguf | Q6_K | 3.31 GB | +| jupyter-agent-qwen3-4b-thinking.Q8_0.gguf | Q8_0 | 4.28 GB | + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +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) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5d0c447 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen3" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.BF16.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.BF16.gguf new file mode 100644 index 0000000..404f109 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eedab7f5f7909f66c91e4e78dd89070d975b1014d738ae74e69fc7073b7ed45 +size 8051285056 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F16.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F16.gguf new file mode 100644 index 0000000..ef391a3 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847c8b4c9091dd598838c15b98252c8917b6ef7dd9f674c1b9e82a7d41cd746a +size 8051285056 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F32.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F32.gguf new file mode 100644 index 0000000..66ca8d3 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4ca1ed1fa621571e34014ee48488e5c1e7f104551a29312e137991bc3cbd10 +size 16095829056 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q2_K.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q2_K.gguf new file mode 100644 index 0000000..b65cafe --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:095407599ca45ac2ea902fa88915d8561a4a073dbe9df57a2fa0fca3409101a1 +size 1669499456 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf new file mode 100644 index 0000000..0a90b33 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afd7403716b365d8ba1f54764deebbce9a673c9c0971eab3baca84b025e1605 +size 2239785536 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf new file mode 100644 index 0000000..11c2bdb --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d99f356e3ca79bd3a35eb15c4b184f20f010de3feb35de78fabf511b0f3884e +size 2075617856 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf new file mode 100644 index 0000000..26f8e78 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c648c5dd8c66c3446a8b69dc8aeff50e618921b739a95a8d5620544bdcf0b4fe +size 1886997056 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf new file mode 100644 index 0000000..a012a1d --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08df1a67f13255dbc6e4a098169ddc690fb6ad443b149085fa4e3c7a1e9d689e +size 2497280576 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf new file mode 100644 index 0000000..b3e1f23 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d408e999c39afa5fcd49c441f1f5c19c337f70d88ff5113ee8e19c5885ebc6a7 +size 2383309376 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf new file mode 100644 index 0000000..209edce --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e99a9f34be9c5ccd757e44dbe7f543b9290e01291a4225e34282c318d48c010 +size 2889513536 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf new file mode 100644 index 0000000..0b1c0d6 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989f809e3e5bce3428cedc5e2fc35e875bc444b31f75e3fb6ed36f1707ac6841 +size 2823711296 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q6_K.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q6_K.gguf new file mode 100644 index 0000000..8e85291 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4e4dd353d854d9156a8d7b7d90a8b678ef2a4546c6c805819d68ed1e987a08 +size 3306261056 diff --git a/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q8_0.gguf b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q8_0.gguf new file mode 100644 index 0000000..ba98cf4 --- /dev/null +++ b/jupyter-agent-qwen3-4b-thinking/ jupyter-agent-qwen3-4b-thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0ffcb9a7b57c119bcbc9338598ff456add6e03edba31eb549851b369a2a92e +size 4280405056