commit 43cfe9bbd452ac9b40c4222b72b0c093aecac43e Author: ModelHub XC Date: Tue May 26 03:11:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InternVL3-8B-Pretrained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..790f733 --- /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 +InternVL3-8B-Pretrained.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.f16.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-8B-Pretrained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InternVL3-8B-Pretrained.IQ4_XS.gguf b/InternVL3-8B-Pretrained.IQ4_XS.gguf new file mode 100644 index 0000000..7d28367 --- /dev/null +++ b/InternVL3-8B-Pretrained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce162f552562e0c4caee3baa8bc3d1e51b29b92096f509ee4cfea8d3bc45f7b +size 4248401408 diff --git a/InternVL3-8B-Pretrained.Q2_K.gguf b/InternVL3-8B-Pretrained.Q2_K.gguf new file mode 100644 index 0000000..1440dfc --- /dev/null +++ b/InternVL3-8B-Pretrained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7101d2b81dfd55a9a28cc7ae9e6f90ecb19ce9db9295c6d6f981fa315edd3e30 +size 3014327072 diff --git a/InternVL3-8B-Pretrained.Q3_K_L.gguf b/InternVL3-8B-Pretrained.Q3_K_L.gguf new file mode 100644 index 0000000..e8de457 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a469a134d1c61ce24f127aa678ede1b070e4d2c926c6cde71de4494ade589fba +size 4086704288 diff --git a/InternVL3-8B-Pretrained.Q3_K_M.gguf b/InternVL3-8B-Pretrained.Q3_K_M.gguf new file mode 100644 index 0000000..21de7c2 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602cd644d08abc4b189e02559e51595efa1d41209912ed063baf43b9bb559f63 +size 3806636192 diff --git a/InternVL3-8B-Pretrained.Q3_K_S.gguf b/InternVL3-8B-Pretrained.Q3_K_S.gguf new file mode 100644 index 0000000..108277c --- /dev/null +++ b/InternVL3-8B-Pretrained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3d0e181ea6f0b9d9847701c986ef8947e6d3c19c82fc553079ab9e305f4fb4 +size 3490613408 diff --git a/InternVL3-8B-Pretrained.Q4_K_M.gguf b/InternVL3-8B-Pretrained.Q4_K_M.gguf new file mode 100644 index 0000000..4b23e79 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e132bf2edf6ae90922094c91c71fcd1ff8bda9c75d927f85d3e4a4ed178fb38e +size 4681132896 diff --git a/InternVL3-8B-Pretrained.Q4_K_S.gguf b/InternVL3-8B-Pretrained.Q4_K_S.gguf new file mode 100644 index 0000000..efc7450 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6873bcd85df3d6c6bb5a3e7351fbea9b63954a98bb897f5ab6f908b579cd7f6c +size 4455828320 diff --git a/InternVL3-8B-Pretrained.Q5_K_M.gguf b/InternVL3-8B-Pretrained.Q5_K_M.gguf new file mode 100644 index 0000000..50cb6b5 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc34e3dc416b44c687570236297165718b15c4a1591813cbee4c7d4470cb468 +size 5442715872 diff --git a/InternVL3-8B-Pretrained.Q5_K_S.gguf b/InternVL3-8B-Pretrained.Q5_K_S.gguf new file mode 100644 index 0000000..38057e0 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6751f29c440442145ad0baf55dbb3a62606a2e3b0b51170086c5bcf643ee66e6 +size 5313061088 diff --git a/InternVL3-8B-Pretrained.Q6_K.gguf b/InternVL3-8B-Pretrained.Q6_K.gguf new file mode 100644 index 0000000..b82422a --- /dev/null +++ b/InternVL3-8B-Pretrained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97f80defd76f06535ff2e3facc2e38730f136aa0c8de41469fec887332608a7 +size 6251897792 diff --git a/InternVL3-8B-Pretrained.Q8_0.gguf b/InternVL3-8B-Pretrained.Q8_0.gguf new file mode 100644 index 0000000..f78eb73 --- /dev/null +++ b/InternVL3-8B-Pretrained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451f56014510216701bc334ca18fb8ef7b77593f9d2a95ce75e618f218191df3 +size 8095547136 diff --git a/InternVL3-8B-Pretrained.f16.gguf b/InternVL3-8B-Pretrained.f16.gguf new file mode 100644 index 0000000..f720b09 --- /dev/null +++ b/InternVL3-8B-Pretrained.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585622ca14ddf4173a1da785b2b549146d8b6b3790ae133a20c2141d6c2e621c +size 15232254336 diff --git a/InternVL3-8B-Pretrained.mmproj-Q8_0.gguf b/InternVL3-8B-Pretrained.mmproj-Q8_0.gguf new file mode 100644 index 0000000..e981356 --- /dev/null +++ b/InternVL3-8B-Pretrained.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3f2980ede368506b1a756c622c287ff84367c19e2223d36844d267482f9882 +size 357082624 diff --git a/InternVL3-8B-Pretrained.mmproj-f16.gguf b/InternVL3-8B-Pretrained.mmproj-f16.gguf new file mode 100644 index 0000000..d1fc3b1 --- /dev/null +++ b/InternVL3-8B-Pretrained.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8422c79a891ece10afb8cb4e4ba9d2e4a4d6451108d23d4c4c55812c27b96206 +size 666002944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b12d1d3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: OpenGVLab/InternVL3-8B-Pretrained +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/InternVL3-8B-Pretrained + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InternVL3-8B-Pretrained-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-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/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.mmproj-f16.gguf) | mmproj-f16 | 0.8 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-8B-Pretrained-GGUF/resolve/main/InternVL3-8B-Pretrained.f16.gguf) | f16 | 15.3 | 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. + +