commit aea8413d68b19d896e8fc65976f5dd6b16568f70 Author: ModelHub XC Date: Mon Jul 20 15:14:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/microsoft_Phi-4-mini-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..6146ad5 --- /dev/null +++ b/README.md @@ -0,0 +1,178 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +widget: +- messages: + - role: user + content: How to solve 3*x^2+4*x+5=1? +language: +- en +license: mit +base_model_relation: quantized +base_model: microsoft/Phi-4-mini-reasoning +tags: +- nlp +- math +- code +license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE +--- + +## Llamacpp imatrix Quantizations of Phi-4-mini-reasoning by microsoft + +Using llama.cpp release b5228 for quantization. + +Original model: https://huggingface.co/microsoft/Phi-4-mini-reasoning + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|system|>Your name is Phi, an AI math expert developed by Microsoft. {system_prompt}<|end|><|user|>{prompt}<|end|><|assistant|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Phi-4-mini-reasoning-bf16.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-bf16.gguf) | bf16 | 7.68GB | false | Full BF16 weights. | +| [Phi-4-mini-reasoning-Q8_0.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q8_0.gguf) | Q8_0 | 4.08GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Phi-4-mini-reasoning-Q6_K_L.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q6_K_L.gguf) | Q6_K_L | 3.30GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Phi-4-mini-reasoning-Q6_K.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q6_K.gguf) | Q6_K | 3.16GB | false | Very high quality, near perfect, *recommended*. | +| [Phi-4-mini-reasoning-Q5_K_L.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q5_K_L.gguf) | Q5_K_L | 3.00GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Phi-4-mini-reasoning-Q5_K_M.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q5_K_M.gguf) | Q5_K_M | 2.85GB | false | High quality, *recommended*. | +| [Phi-4-mini-reasoning-Q5_K_S.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q5_K_S.gguf) | Q5_K_S | 2.73GB | false | High quality, *recommended*. | +| [Phi-4-mini-reasoning-Q4_K_L.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q4_K_L.gguf) | Q4_K_L | 2.64GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Phi-4-mini-reasoning-Q4_1.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q4_1.gguf) | Q4_1 | 2.53GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Phi-4-mini-reasoning-Q4_K_M.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf) | Q4_K_M | 2.49GB | false | Good quality, default size for most use cases, *recommended*. | +| [Phi-4-mini-reasoning-Q3_K_XL.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q3_K_XL.gguf) | Q3_K_XL | 2.40GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Phi-4-mini-reasoning-Q4_K_S.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q4_K_S.gguf) | Q4_K_S | 2.34GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Phi-4-mini-reasoning-Q4_0.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q4_0.gguf) | Q4_0 | 2.33GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Phi-4-mini-reasoning-IQ4_NL.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ4_NL.gguf) | IQ4_NL | 2.33GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Phi-4-mini-reasoning-Q3_K_L.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q3_K_L.gguf) | Q3_K_L | 2.25GB | false | Lower quality but usable, good for low RAM availability. | +| [Phi-4-mini-reasoning-IQ4_XS.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ4_XS.gguf) | IQ4_XS | 2.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Phi-4-mini-reasoning-Q3_K_M.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q3_K_M.gguf) | Q3_K_M | 2.12GB | false | Low quality. | +| [Phi-4-mini-reasoning-IQ3_M.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ3_M.gguf) | IQ3_M | 2.02GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Phi-4-mini-reasoning-Q3_K_S.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q3_K_S.gguf) | Q3_K_S | 1.90GB | false | Low quality, not recommended. | +| [Phi-4-mini-reasoning-IQ3_XS.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ3_XS.gguf) | IQ3_XS | 1.84GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Phi-4-mini-reasoning-Q2_K_L.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q2_K_L.gguf) | Q2_K_L | 1.83GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Phi-4-mini-reasoning-IQ3_XXS.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ3_XXS.gguf) | IQ3_XXS | 1.68GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Phi-4-mini-reasoning-Q2_K.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-Q2_K.gguf) | Q2_K | 1.68GB | false | Very low quality but surprisingly usable. | +| [Phi-4-mini-reasoning-IQ2_M.gguf](https://huggingface.co/bartowski/microsoft_Phi-4-mini-reasoning-GGUF/blob/main/microsoft_Phi-4-mini-reasoning-IQ2_M.gguf) | IQ2_M | 1.51GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/microsoft_Phi-4-mini-reasoning-GGUF --include "microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/microsoft_Phi-4-mini-reasoning-GGUF --include "microsoft_Phi-4-mini-reasoning-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (microsoft_Phi-4-mini-reasoning-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/microsoft_Phi-4-mini-reasoning-IQ2_M.gguf b/microsoft_Phi-4-mini-reasoning-IQ2_M.gguf new file mode 100644 index 0000000..640b940 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e9c72d51f8c08c82ed0558bea0d768b7ac1b8a2f93cd2c5f2d8172ad6a245e +size 1507424800 diff --git a/microsoft_Phi-4-mini-reasoning-IQ3_M.gguf b/microsoft_Phi-4-mini-reasoning-IQ3_M.gguf new file mode 100644 index 0000000..58016c1 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9732d467dc726552353bdcd3146449d22be143ed2797443c7bbb09c1f50269 +size 2017656352 diff --git a/microsoft_Phi-4-mini-reasoning-IQ3_XS.gguf b/microsoft_Phi-4-mini-reasoning-IQ3_XS.gguf new file mode 100644 index 0000000..3996348 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b11d76a491249c4afb39e2e2527e8b9e71e963c69edc839e43ebe34d7ea26d +size 1840709152 diff --git a/microsoft_Phi-4-mini-reasoning-IQ3_XXS.gguf b/microsoft_Phi-4-mini-reasoning-IQ3_XXS.gguf new file mode 100644 index 0000000..4081d6f --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff4dad6f68d8318f6c2cc34441ec62d4d69022f0ba4f5041f3635f75bcb97dbf +size 1678866976 diff --git a/microsoft_Phi-4-mini-reasoning-IQ4_NL.gguf b/microsoft_Phi-4-mini-reasoning-IQ4_NL.gguf new file mode 100644 index 0000000..c3417ab --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb44fe8455b81674aa49307590eaf22b3e4cf138dfef25eb33aef11627c1c9c +size 2325151264 diff --git a/microsoft_Phi-4-mini-reasoning-IQ4_XS.gguf b/microsoft_Phi-4-mini-reasoning-IQ4_XS.gguf new file mode 100644 index 0000000..d9005a8 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ca9619e75ce8c760c967c6e9a95231933dd24c46b1f1ace3a4c9d7d446a9d2 +size 2224487968 diff --git a/microsoft_Phi-4-mini-reasoning-Q2_K.gguf b/microsoft_Phi-4-mini-reasoning-Q2_K.gguf new file mode 100644 index 0000000..fa78ae3 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169cdb82775f9c62b39d825f296a86c2d86f0a237b3d4b53fc4b88ff0491f547 +size 1682636320 diff --git a/microsoft_Phi-4-mini-reasoning-Q2_K_L.gguf b/microsoft_Phi-4-mini-reasoning-Q2_K_L.gguf new file mode 100644 index 0000000..8bf12cd --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff1dc7767d03ad570eca4250abc4833ffd4402ee303dacb6e6d86d7a69eafe7 +size 1831483936 diff --git a/microsoft_Phi-4-mini-reasoning-Q3_K_L.gguf b/microsoft_Phi-4-mini-reasoning-Q3_K_L.gguf new file mode 100644 index 0000000..7a3e898 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869fbc23f326dd75d29b48eb69fa11c6bffde95d8836fed534f9839bbd560464 +size 2249653792 diff --git a/microsoft_Phi-4-mini-reasoning-Q3_K_M.gguf b/microsoft_Phi-4-mini-reasoning-Q3_K_M.gguf new file mode 100644 index 0000000..559965f --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b090988b856fd6ae3b66d55846614d176b92ef52741833fced67b12a02e5b223 +size 2117533216 diff --git a/microsoft_Phi-4-mini-reasoning-Q3_K_S.gguf b/microsoft_Phi-4-mini-reasoning-Q3_K_S.gguf new file mode 100644 index 0000000..4be2cd1 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9a6f68c3e6587cf013d5d470b989fd7610ddf01c51f1b6a66b2c054dfeabe8 +size 1897332256 diff --git a/microsoft_Phi-4-mini-reasoning-Q3_K_XL.gguf b/microsoft_Phi-4-mini-reasoning-Q3_K_XL.gguf new file mode 100644 index 0000000..9b3dd41 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9730b9ae92b7bc55569492569bcdaa1ab657e777a2bcefd67bd98dafc14f3631 +size 2398501408 diff --git a/microsoft_Phi-4-mini-reasoning-Q4_0.gguf b/microsoft_Phi-4-mini-reasoning-Q4_0.gguf new file mode 100644 index 0000000..fb47cd6 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8843380786f086d3dad15af84d5e8b292e7ef57e4526f2910778ad04a12c719 +size 2331442720 diff --git a/microsoft_Phi-4-mini-reasoning-Q4_1.gguf b/microsoft_Phi-4-mini-reasoning-Q4_1.gguf new file mode 100644 index 0000000..9785334 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211351b8382f235756c9880ee09f3a3c9b4d2506d88c41bb95f3cff2b348f39f +size 2526477856 diff --git a/microsoft_Phi-4-mini-reasoning-Q4_K_L.gguf b/microsoft_Phi-4-mini-reasoning-Q4_K_L.gguf new file mode 100644 index 0000000..ea120c3 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd1f2f7930bd2b84a666c06b5f0f501709faf12024ad34a22c9b621307ac9c5 +size 2640722464 diff --git a/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf b/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf new file mode 100644 index 0000000..05cbf0f --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8becd58f350d8ae0ec3bbb201ab36f750ffab17ab6238f39292d12ab68ea06 +size 2491874848 diff --git a/microsoft_Phi-4-mini-reasoning-Q4_K_S.gguf b/microsoft_Phi-4-mini-reasoning-Q4_K_S.gguf new file mode 100644 index 0000000..1cc7656 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d5a4b7bcf956e00dec03e9bed68cf0543d225806b11941cfb9630b00af71ed4 +size 2337734176 diff --git a/microsoft_Phi-4-mini-reasoning-Q5_K_L.gguf b/microsoft_Phi-4-mini-reasoning-Q5_K_L.gguf new file mode 100644 index 0000000..4adc4ef --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e656a0feb7c5fa6346a41e0df0d07904345e8ab98df073b73172c513a01de3 +size 2996976160 diff --git a/microsoft_Phi-4-mini-reasoning-Q5_K_M.gguf b/microsoft_Phi-4-mini-reasoning-Q5_K_M.gguf new file mode 100644 index 0000000..8058721 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daabb3e23ca39e969ccd1ee8eec731a164f3c1754bbc70ce946a474ce4df0d7b +size 2848128544 diff --git a/microsoft_Phi-4-mini-reasoning-Q5_K_S.gguf b/microsoft_Phi-4-mini-reasoning-Q5_K_S.gguf new file mode 100644 index 0000000..5052f77 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cb31d96ca269cce239693b75d9e496b19f8ba9fe8f78c019d3011d1d3aaa0c +size 2727804448 diff --git a/microsoft_Phi-4-mini-reasoning-Q6_K.gguf b/microsoft_Phi-4-mini-reasoning-Q6_K.gguf new file mode 100644 index 0000000..60a4b42 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1313ebb6e39814c4d2f09bd41116b71327793267737a57dd362bbf07b040a0f +size 3155623456 diff --git a/microsoft_Phi-4-mini-reasoning-Q6_K_L.gguf b/microsoft_Phi-4-mini-reasoning-Q6_K_L.gguf new file mode 100644 index 0000000..e46a7ad --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060e5b4f5a829db29309c4d092f720fce6d7e7b94daeb6d78c8ab4fc96213c1d +size 3304471072 diff --git a/microsoft_Phi-4-mini-reasoning-Q8_0.gguf b/microsoft_Phi-4-mini-reasoning-Q8_0.gguf new file mode 100644 index 0000000..f2140d6 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817d5441f36965e8cca18018a9b8e6f6f7cd52e5deb0d3f245c44590d6a010f1 +size 4084611616 diff --git a/microsoft_Phi-4-mini-reasoning-bf16.gguf b/microsoft_Phi-4-mini-reasoning-bf16.gguf new file mode 100644 index 0000000..94c7695 --- /dev/null +++ b/microsoft_Phi-4-mini-reasoning-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75aa5b2c99197933f3b3051ec99c1ff1a711a2bcafd6d8eb9bbb64f19b8e3ea +size 7680694528 diff --git a/microsoft_Phi-4-mini-reasoning.imatrix b/microsoft_Phi-4-mini-reasoning.imatrix new file mode 100644 index 0000000..5fdd730 Binary files /dev/null and b/microsoft_Phi-4-mini-reasoning.imatrix differ