commit 1d1a49064af757efddac92145f3ce8d6c969fa6b 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/InternVL3-1B-Pretrained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..be00c6c --- /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 +InternVL3-1B-Pretrained.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InternVL3-1B-Pretrained.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InternVL3-1B-Pretrained.IQ4_XS.gguf b/InternVL3-1B-Pretrained.IQ4_XS.gguf new file mode 100644 index 0000000..3e52707 --- /dev/null +++ b/InternVL3-1B-Pretrained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f43c2187cbcef2ba40c348b1369af6df66439cdcee74db874c73a27413bbd821 +size 427634368 diff --git a/InternVL3-1B-Pretrained.Q2_K.gguf b/InternVL3-1B-Pretrained.Q2_K.gguf new file mode 100644 index 0000000..7cae66f --- /dev/null +++ b/InternVL3-1B-Pretrained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57bff3e9ecbfbabe698be04442f42eace11ea1d89c3858f8689984d6cc9c6df5 +size 414796480 diff --git a/InternVL3-1B-Pretrained.Q3_K_L.gguf b/InternVL3-1B-Pretrained.Q3_K_L.gguf new file mode 100644 index 0000000..e14be8f --- /dev/null +++ b/InternVL3-1B-Pretrained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4cf81eb212a3e70ff5b4eae02e5b7d67e3628793f5d3834b953c6a2fbdd18d +size 445547200 diff --git a/InternVL3-1B-Pretrained.Q3_K_M.gguf b/InternVL3-1B-Pretrained.Q3_K_M.gguf new file mode 100644 index 0000000..eea708d --- /dev/null +++ b/InternVL3-1B-Pretrained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f743d81f6a2898358a0a0943181adcea9d44a599072d76d370eaecb021e04ee0 +size 431655616 diff --git a/InternVL3-1B-Pretrained.Q3_K_S.gguf b/InternVL3-1B-Pretrained.Q3_K_S.gguf new file mode 100644 index 0000000..645b215 --- /dev/null +++ b/InternVL3-1B-Pretrained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25b3285e7194bc03e928ad505fae50a69ed1f4e21d59164c3b5248d1cb90cfd +size 414452416 diff --git a/InternVL3-1B-Pretrained.Q4_K_M.gguf b/InternVL3-1B-Pretrained.Q4_K_M.gguf new file mode 100644 index 0000000..1f162bc --- /dev/null +++ b/InternVL3-1B-Pretrained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb5b6bf4819ba4e2b30fa6bd612e575f8e7a5c2767e1ce32a3431af614eec7b +size 490984480 diff --git a/InternVL3-1B-Pretrained.Q4_K_S.gguf b/InternVL3-1B-Pretrained.Q4_K_S.gguf new file mode 100644 index 0000000..a378c2c --- /dev/null +++ b/InternVL3-1B-Pretrained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:204550d40ab293996388c7871d80a1eb145ff333ba84df6e893e53d7428feef2 +size 478648352 diff --git a/InternVL3-1B-Pretrained.Q5_K_M.gguf b/InternVL3-1B-Pretrained.Q5_K_M.gguf new file mode 100644 index 0000000..426aa5e --- /dev/null +++ b/InternVL3-1B-Pretrained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bee001c1faf7d1c4cda07cc30d1bce4f6d72fc1f0c644c32254631595bbbae6 +size 521756352 diff --git a/InternVL3-1B-Pretrained.Q5_K_S.gguf b/InternVL3-1B-Pretrained.Q5_K_S.gguf new file mode 100644 index 0000000..5cb1fbd --- /dev/null +++ b/InternVL3-1B-Pretrained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:742468a7fc8ea1acaef6e215c940f0d1051c654eeae0a2fb784ea358599dbf6c +size 514380480 diff --git a/InternVL3-1B-Pretrained.Q6_K.gguf b/InternVL3-1B-Pretrained.Q6_K.gguf new file mode 100644 index 0000000..85b655f --- /dev/null +++ b/InternVL3-1B-Pretrained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9f69433443458e6cc9969f8c8c2316cb6dc6ece1e55953e6970c7488a03cb3 +size 649875520 diff --git a/InternVL3-1B-Pretrained.Q8_0.gguf b/InternVL3-1B-Pretrained.Q8_0.gguf new file mode 100644 index 0000000..3afa3ae --- /dev/null +++ b/InternVL3-1B-Pretrained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c46cbb7bcc86ec73d54e74df2bf86c098e30b89b0ab9e26acecd020ccabea123 +size 675207232 diff --git a/InternVL3-1B-Pretrained.f16.gguf b/InternVL3-1B-Pretrained.f16.gguf new file mode 100644 index 0000000..ed44c11 --- /dev/null +++ b/InternVL3-1B-Pretrained.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097d6d29be2a10d03b1abe3193a00cf04fc7179d91f7090f14858795b27043d7 +size 1265481920 diff --git a/InternVL3-1B-Pretrained.mmproj-Q8_0.gguf b/InternVL3-1B-Pretrained.mmproj-Q8_0.gguf new file mode 100644 index 0000000..63d5db7 --- /dev/null +++ b/InternVL3-1B-Pretrained.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54d223fb67e50c1f313758d7eac0a025d4ddb49f592f3f35f2c6e6f87135d56 +size 332568064 diff --git a/InternVL3-1B-Pretrained.mmproj-f16.gguf b/InternVL3-1B-Pretrained.mmproj-f16.gguf new file mode 100644 index 0000000..0d8f56d --- /dev/null +++ b/InternVL3-1B-Pretrained.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388a0c942f3fc7a20048432129a97fb05bd56234cb2db9eeda3ae4631df46d20 +size 619876864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cf28ba2 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: OpenGVLab/InternVL3-1B-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/InternVL3-1B-Pretrained + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InternVL3-1B-Pretrained-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InternVL3-1B-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/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.mmproj-f16.gguf) | mmproj-f16 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.Q8_0.gguf) | Q8_0 | 0.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InternVL3-1B-Pretrained-GGUF/resolve/main/InternVL3-1B-Pretrained.f16.gguf) | f16 | 1.4 | 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. + +