commit 424e7db61db22575f2253b1bf1d1e08ffb17fb66 Author: ModelHub XC Date: Mon May 25 22:34:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-4-mini-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1652157 --- /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 +Phi-4-mini-reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-4-mini-reasoning.IQ4_XS.gguf b/Phi-4-mini-reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..e59a864 --- /dev/null +++ b/Phi-4-mini-reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d852fe3d1364cbd733cd51c5371ff9e81705e230f46ab0f3f49590223d988a +size 2240216800 diff --git a/Phi-4-mini-reasoning.Q2_K.gguf b/Phi-4-mini-reasoning.Q2_K.gguf new file mode 100644 index 0000000..0e6f00a --- /dev/null +++ b/Phi-4-mini-reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783301f0fac06542b7d9911e884a27b41144cd052c0f05e48a10209adf55f160 +size 1682636512 diff --git a/Phi-4-mini-reasoning.Q3_K_L.gguf b/Phi-4-mini-reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..fd0a21e --- /dev/null +++ b/Phi-4-mini-reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2845e0d5837c34006b3f149af216f5ac7b85ca7d4904b5efbe9afce03f36e98f +size 2249653984 diff --git a/Phi-4-mini-reasoning.Q3_K_M.gguf b/Phi-4-mini-reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..5e47992 --- /dev/null +++ b/Phi-4-mini-reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c45c53d03bcc3e36e68d8401d97d4022ed57898570f244026fe54db8a1550d +size 2117533408 diff --git a/Phi-4-mini-reasoning.Q3_K_S.gguf b/Phi-4-mini-reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..39a25f7 --- /dev/null +++ b/Phi-4-mini-reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968c57503d61317065955f152f7c02909ff9701d04784bb3a1087ca0ce4a43db +size 1897332448 diff --git a/Phi-4-mini-reasoning.Q4_K_M.gguf b/Phi-4-mini-reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..3d6e43b --- /dev/null +++ b/Phi-4-mini-reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c7bae9b58af92251e7a6f64a7f45ce9a8ad752778051a42a9496a31a94e3a6 +size 2491875040 diff --git a/Phi-4-mini-reasoning.Q4_K_S.gguf b/Phi-4-mini-reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..731bd2d --- /dev/null +++ b/Phi-4-mini-reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc769f005aaba7e51ffab96a4935ae6929dedf28d5fce740b799d247b72fa6d4 +size 2337734368 diff --git a/Phi-4-mini-reasoning.Q5_K_M.gguf b/Phi-4-mini-reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..bc2d736 --- /dev/null +++ b/Phi-4-mini-reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b91816a1c48b7b84e265944cf4b59d3e28bfa22dc8bb561bcd2ec29087e0b23 +size 2848128736 diff --git a/Phi-4-mini-reasoning.Q5_K_S.gguf b/Phi-4-mini-reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..8aaeb05 --- /dev/null +++ b/Phi-4-mini-reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89d6359316910e9fc0909fdd4c2bdfd1123ccaf2a912e8c706820e2f95e8c6a +size 2727804640 diff --git a/Phi-4-mini-reasoning.Q6_K.gguf b/Phi-4-mini-reasoning.Q6_K.gguf new file mode 100644 index 0000000..af091da --- /dev/null +++ b/Phi-4-mini-reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869f0df473c0eb65d0d7f50aad0eca2a4fed0db32dfb8f96da626ccbd7f3a372 +size 3155623648 diff --git a/Phi-4-mini-reasoning.Q8_0.gguf b/Phi-4-mini-reasoning.Q8_0.gguf new file mode 100644 index 0000000..d778221 --- /dev/null +++ b/Phi-4-mini-reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf42c7487b2b844a467b621b9d75df0114dfd19e0a046f96ed4c8d54183c976c +size 4084611808 diff --git a/Phi-4-mini-reasoning.f16.gguf b/Phi-4-mini-reasoning.f16.gguf new file mode 100644 index 0000000..11f48a9 --- /dev/null +++ b/Phi-4-mini-reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d115b6ad62d66a869014b02970f4b555138b6e2d7eed7a29ddcc2d5b00696b26 +size 7680695008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ffa264a --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: microsoft/Phi-4-mini-reasoning +language: +- en +library_name: transformers +license: mit +license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nlp +- math +- code +--- +## About + + + + + + +static quants of https://huggingface.co/microsoft/Phi-4-mini-reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phi-4-mini-reasoning-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi-4-mini-reasoning-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/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q5_K_S.gguf) | Q5_K_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-4-mini-reasoning-GGUF/resolve/main/Phi-4-mini-reasoning.f16.gguf) | f16 | 7.8 | 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. + +