commit 0b917bed0b49ccdb28244ed23e6ea8188a68a21a Author: ModelHub XC Date: Thu Jun 11 10:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InternVL3-2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..09f78df --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +InternVL3-2B-Instruct.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InternVL3-2B-Instruct.IQ4_XS.gguf b/InternVL3-2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..0c89ba9 --- /dev/null +++ b/InternVL3-2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551d5f660b21ca59aa05f8cb10c88b78f89025cc6fb00747931b7c5128e84671 +size 1025613312 diff --git a/InternVL3-2B-Instruct.Q2_K.gguf b/InternVL3-2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..89f079b --- /dev/null +++ b/InternVL3-2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1b6c50316b886410b7d44fb04b9c17480ddcc823acd7db4edc86a4e8bc7062 +size 752413024 diff --git a/InternVL3-2B-Instruct.Q3_K_L.gguf b/InternVL3-2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..5578703 --- /dev/null +++ b/InternVL3-2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236bf4383b24be0d4de61350ecab579d365c7b12a8dc1526e058809dd0dba09d +size 979932096 diff --git a/InternVL3-2B-Instruct.Q3_K_M.gguf b/InternVL3-2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..84ec6ca --- /dev/null +++ b/InternVL3-2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e9422aeac0ef5cbc3465b503a193f3c93f971d8d9ac230e26392fa3da51489 +size 923947968 diff --git a/InternVL3-2B-Instruct.Q3_K_S.gguf b/InternVL3-2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5392a50 --- /dev/null +++ b/InternVL3-2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a74217f2fba1d4bae4590346c7fb53483ba9031f18323a3432f1d8a74c4e21 +size 860713920 diff --git a/InternVL3-2B-Instruct.Q4_K_M.gguf b/InternVL3-2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..466c4c7 --- /dev/null +++ b/InternVL3-2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda20a1b998e9f74c007a8893cdb78a3d87db8e2e4927b8554ae01e85b5f4634 +size 1116759264 diff --git a/InternVL3-2B-Instruct.Q4_K_S.gguf b/InternVL3-2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e1cdba9 --- /dev/null +++ b/InternVL3-2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f5605244e32f539dc3cf6407ad3f71ab29aa666d45d9cdfdfa90ca8d294641 +size 1071023328 diff --git a/InternVL3-2B-Instruct.Q5_K_M.gguf b/InternVL3-2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..93fa0fb --- /dev/null +++ b/InternVL3-2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0c3bbc11e8073c8ef14419b40027b8a32e108ad63b91a8d87fbff901270c7c +size 1284882528 diff --git a/InternVL3-2B-Instruct.Q5_K_S.gguf b/InternVL3-2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..631b218 --- /dev/null +++ b/InternVL3-2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbedc7304e4b18abb95dd82a296420ec802b4fdf05792436ccbfd617f05cec9 +size 1258561632 diff --git a/InternVL3-2B-Instruct.Q6_K.gguf b/InternVL3-2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..aaeb5c6 --- /dev/null +++ b/InternVL3-2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c538450aab2f695fdb1f4d163ac7284e1dc20d45490c1ffb99ca1882b3aef4c5 +size 1463513504 diff --git a/InternVL3-2B-Instruct.Q8_0.gguf b/InternVL3-2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..5398305 --- /dev/null +++ b/InternVL3-2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020ec4b8db1a30245639269e43a6a764bf592553b42d9f26407d17e8670f892d +size 1893671968 diff --git a/InternVL3-2B-Instruct.f16.gguf b/InternVL3-2B-Instruct.f16.gguf new file mode 100644 index 0000000..f8e1bbc --- /dev/null +++ b/InternVL3-2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5208b5563deff883e31e6314c1dff5c2d9d8070cb5af3231486231fb939dcf6c +size 3558801568 diff --git a/InternVL3-2B-Instruct.mmproj-Q8_0.gguf b/InternVL3-2B-Instruct.mmproj-Q8_0.gguf new file mode 100644 index 0000000..908e04f --- /dev/null +++ b/InternVL3-2B-Instruct.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91c525291f65b0469f82544e82f202c4df1c093268f0ce27deec10664078a0c +size 337012000 diff --git a/InternVL3-2B-Instruct.mmproj-f16.gguf b/InternVL3-2B-Instruct.mmproj-f16.gguf new file mode 100644 index 0000000..544d413 --- /dev/null +++ b/InternVL3-2B-Instruct.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e6f0663d591169e8ddd2f415262cef2a5a994705658841e56c09401a54deb3 +size 628237600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d350fce --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: OpenGVLab/InternVL3-2B-Instruct +language: +- multilingual +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE +license_name: qwen +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- internvl +- custom_code +--- +## About + + + + + + +static quants of https://huggingface.co/OpenGVLab/InternVL3-2B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InternVL3-2B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InternVL3-2B-Instruct-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/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.mmproj-f16.gguf) | mmproj-f16 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-2B-Instruct-GGUF/resolve/main/InternVL3-2B-Instruct.f16.gguf) | f16 | 3.7 | 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. + +