commit 0487af6511a5c2c7bba2f98838a5780801158578 Author: ModelHub XC Date: Fri May 15 21:14:07 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Voxtral-Mini-3B-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e4e845 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Voxtral-Mini-3B-2507.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Voxtral-Mini-3B-2507.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b5c8868 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: mistralai/Voxtral-Mini-3B-2507 +language: +- en +- fr +- de +- es +- it +- pt +- nl +- hi +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vllm +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mistralai/Voxtral-Mini-3B-2507 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Voxtral-Mini-3B-2507-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-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/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Voxtral-Mini-3B-2507-GGUF/resolve/main/Voxtral-Mini-3B-2507.f16.gguf) | f16 | 8.1 | 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. + + diff --git a/Voxtral-Mini-3B-2507.IQ4_XS.gguf b/Voxtral-Mini-3B-2507.IQ4_XS.gguf new file mode 100644 index 0000000..7347da8 --- /dev/null +++ b/Voxtral-Mini-3B-2507.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fccd0b69ce7372b9e16244f6224d6ae0bf24100421a8c0ac23ced6391efb7ce7 +size 2284504576 diff --git a/Voxtral-Mini-3B-2507.Q2_K.gguf b/Voxtral-Mini-3B-2507.Q2_K.gguf new file mode 100644 index 0000000..f5ed042 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d5bbe50f42deb073e8b47c93586f376e5d4115f2ff11922f8f85b1af5065fd +size 1661552128 diff --git a/Voxtral-Mini-3B-2507.Q3_K_L.gguf b/Voxtral-Mini-3B-2507.Q3_K_L.gguf new file mode 100644 index 0000000..8cd74ea --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38cfd994e4100c7dd1bc3ec804471e78c44179cb6b3cae56b7b3a485f104345 +size 2207483392 diff --git a/Voxtral-Mini-3B-2507.Q3_K_M.gguf b/Voxtral-Mini-3B-2507.Q3_K_M.gguf new file mode 100644 index 0000000..c227c21 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c85077d6dad7baf4efff4309aeea54afb8ac4dcbafb593cbb5b59a574f3df2 +size 2058061312 diff --git a/Voxtral-Mini-3B-2507.Q3_K_S.gguf b/Voxtral-Mini-3B-2507.Q3_K_S.gguf new file mode 100644 index 0000000..f8aa760 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4883dfd81d6c2c38d9808748172dbcd9935830af828f578ed29e273cdbd80563 +size 1891190272 diff --git a/Voxtral-Mini-3B-2507.Q4_K_M.gguf b/Voxtral-Mini-3B-2507.Q4_K_M.gguf new file mode 100644 index 0000000..dd8a53e --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49588ed04186f2b441679b57c2b0fc3b1c724bbd7349b41a4188134e7a31a42b +size 2473002496 diff --git a/Voxtral-Mini-3B-2507.Q4_K_S.gguf b/Voxtral-Mini-3B-2507.Q4_K_S.gguf new file mode 100644 index 0000000..6a7c19b --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52cb69756249848f17e237e9462a594e26ed0ffa2b865a130b867bfd4952e077 +size 2381825536 diff --git a/Voxtral-Mini-3B-2507.Q5_K_M.gguf b/Voxtral-Mini-3B-2507.Q5_K_M.gguf new file mode 100644 index 0000000..fe09a46 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a8d7025c4f8ebd9b93c163cc1062d54754f1e9e793681b40963e3f0a4193d0 +size 2874869248 diff --git a/Voxtral-Mini-3B-2507.Q5_K_S.gguf b/Voxtral-Mini-3B-2507.Q5_K_S.gguf new file mode 100644 index 0000000..d5b9a6e --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57e8e258b3036d9abf1dc29ba0e421d0f8b23d0fa82a45067776c64ccd7e548 +size 2822227456 diff --git a/Voxtral-Mini-3B-2507.Q6_K.gguf b/Voxtral-Mini-3B-2507.Q6_K.gguf new file mode 100644 index 0000000..1818453 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bff16edd2b8ab4ff935a0fa3a190a84fc42e7d3fd1b51d8aef6ad297c52f89 +size 3301852672 diff --git a/Voxtral-Mini-3B-2507.Q8_0.gguf b/Voxtral-Mini-3B-2507.Q8_0.gguf new file mode 100644 index 0000000..679c564 --- /dev/null +++ b/Voxtral-Mini-3B-2507.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11be38ecfffcd02f5a033a3ff12e610e057ef957eb3a596bcd5681a0854bbacb +size 4273980928 diff --git a/Voxtral-Mini-3B-2507.f16.gguf b/Voxtral-Mini-3B-2507.f16.gguf new file mode 100644 index 0000000..2875442 --- /dev/null +++ b/Voxtral-Mini-3B-2507.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d545ca235fa355a44dadf179f066af638b374cd0768001fd816dbf2d4579f341 +size 8037058048