commit bedb007961724cc050692e651e54433fc31262f8 Author: ModelHub XC Date: Mon May 11 17:40:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-1.2B-JP-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd71991 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +LFM2.5-1.2B-JP.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-JP.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-1.2B-JP.i1-IQ1_M.gguf b/LFM2.5-1.2B-JP.i1-IQ1_M.gguf new file mode 100644 index 0000000..007affb --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2613779c85ac85f3a486d5e4188983e312dabb7060faaf39d611c4a9ed81993e +size 327145120 diff --git a/LFM2.5-1.2B-JP.i1-IQ1_S.gguf b/LFM2.5-1.2B-JP.i1-IQ1_S.gguf new file mode 100644 index 0000000..6c7de91 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0189db7aa0d9df3c4f5c4811e3f43b55a865e63d3cdda0d15a9aa921d8826b +size 304387744 diff --git a/LFM2.5-1.2B-JP.i1-IQ2_M.gguf b/LFM2.5-1.2B-JP.i1-IQ2_M.gguf new file mode 100644 index 0000000..925be7f --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb74655e15aaf4ef335bab83fb4cad4bad38161bbf22315ca11d8ea4ae39497 +size 434132640 diff --git a/LFM2.5-1.2B-JP.i1-IQ2_S.gguf b/LFM2.5-1.2B-JP.i1-IQ2_S.gguf new file mode 100644 index 0000000..ea6bf59 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fafa061d4b935a8f935b8fa313100c1744e8d3ea810878c35c138054da7b357 +size 403789472 diff --git a/LFM2.5-1.2B-JP.i1-IQ2_XS.gguf b/LFM2.5-1.2B-JP.i1-IQ2_XS.gguf new file mode 100644 index 0000000..08259cc --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa912daeaaf93fee57d083e17b3913edb87a0e473a89aa02fa0996db34987d86 +size 396203680 diff --git a/LFM2.5-1.2B-JP.i1-IQ2_XXS.gguf b/LFM2.5-1.2B-JP.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8dca745 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfa7d050884d4023eb450e03af343cad0444a29f6489be4cd7881ee990384da +size 365074080 diff --git a/LFM2.5-1.2B-JP.i1-IQ3_M.gguf b/LFM2.5-1.2B-JP.i1-IQ3_M.gguf new file mode 100644 index 0000000..07a6a7b --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6247865dcc3838e4c500ff6326bd57e29f991cd7ba5ed13206090f7690af9805 +size 566793888 diff --git a/LFM2.5-1.2B-JP.i1-IQ3_S.gguf b/LFM2.5-1.2B-JP.i1-IQ3_S.gguf new file mode 100644 index 0000000..eb0771d --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a232404a9d2ebe5f436a98a4b798ebb2cef7dd3193f58a3d32bacc111af534 +size 558159520 diff --git a/LFM2.5-1.2B-JP.i1-IQ3_XS.gguf b/LFM2.5-1.2B-JP.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3e015ba --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414263779e10056ad5cb7672365169141cdf66ea83819891b03e9343faf0bec9 +size 537810592 diff --git a/LFM2.5-1.2B-JP.i1-IQ3_XXS.gguf b/LFM2.5-1.2B-JP.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..741fa96 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cd6c4ebddaf9458acdf2be83ac688db31e83e70fc8202942c93e25e030be28 +size 490985120 diff --git a/LFM2.5-1.2B-JP.i1-IQ4_NL.gguf b/LFM2.5-1.2B-JP.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f8f37af --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811af7e4a9d4aeaf1366c19ab6bf3baafa6a79037c372d73e88acc0fc59d40f8 +size 695752352 diff --git a/LFM2.5-1.2B-JP.i1-IQ4_XS.gguf b/LFM2.5-1.2B-JP.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fdcc4ba --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1317bf5328c5009fb23d3855e4e452a44012b69d7f9225e67b91a42bc4e2fe +size 663377568 diff --git a/LFM2.5-1.2B-JP.i1-Q2_K.gguf b/LFM2.5-1.2B-JP.i1-Q2_K.gguf new file mode 100644 index 0000000..0571974 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4958180d75508a6ad07e27c52fe0f54b9a358d60c9fd04d263bb3cbd899e8979 +size 483399328 diff --git a/LFM2.5-1.2B-JP.i1-Q2_K_S.gguf b/LFM2.5-1.2B-JP.i1-Q2_K_S.gguf new file mode 100644 index 0000000..38ce5dc --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e1d490497037e5b49518988259fadf4b5127c6a659e0a19dc88097f72a6d31 +size 460805792 diff --git a/LFM2.5-1.2B-JP.i1-Q3_K_L.gguf b/LFM2.5-1.2B-JP.i1-Q3_K_L.gguf new file mode 100644 index 0000000..84786b8 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dcff0508ef0c672e3e6782f21a601d3e4113dc1de3045a352d60e395cd93d02 +size 635475616 diff --git a/LFM2.5-1.2B-JP.i1-Q3_K_M.gguf b/LFM2.5-1.2B-JP.i1-Q3_K_M.gguf new file mode 100644 index 0000000..89bebcf --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b7cd7a09d439a7bab806ede79479e091a58db7a07462078f2a0c6044bc7aa3 +size 600348320 diff --git a/LFM2.5-1.2B-JP.i1-Q3_K_S.gguf b/LFM2.5-1.2B-JP.i1-Q3_K_S.gguf new file mode 100644 index 0000000..de7ff44 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5be533094b2198d921f8addad28908d9d8a8a9323a7c716447cf1f706572eda +size 558159520 diff --git a/LFM2.5-1.2B-JP.i1-Q4_0.gguf b/LFM2.5-1.2B-JP.i1-Q4_0.gguf new file mode 100644 index 0000000..bdad04f --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eae59337569918790c1a86f4d2bde2e9a471de9efffc2819c99f2221d68431d +size 697849504 diff --git a/LFM2.5-1.2B-JP.i1-Q4_1.gguf b/LFM2.5-1.2B-JP.i1-Q4_1.gguf new file mode 100644 index 0000000..2cc5531 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe41b3999bb52b3babb5e65e96eb560ff67abcb1a28d7b73f4dbd2425e680f52 +size 760501920 diff --git a/LFM2.5-1.2B-JP.i1-Q4_K_M.gguf b/LFM2.5-1.2B-JP.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9cbf42e --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:746c6997edceb1ff80f38215eb0df1a875c5d0b758a26e6a97bc84ec42e7889e +size 730896032 diff --git a/LFM2.5-1.2B-JP.i1-Q4_K_S.gguf b/LFM2.5-1.2B-JP.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d09f1c0 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5195d6d890b37171a0f81b939d4d7f87be168396272022755b68b55442d27d7 +size 700470944 diff --git a/LFM2.5-1.2B-JP.i1-Q5_K_M.gguf b/LFM2.5-1.2B-JP.i1-Q5_K_M.gguf new file mode 100644 index 0000000..eab9a36 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ade7ab662d13dc79d98be50614fecc8d56824439b2bace568fa69e66ae71f5f +size 843355808 diff --git a/LFM2.5-1.2B-JP.i1-Q5_K_S.gguf b/LFM2.5-1.2B-JP.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6a4345f --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2abc914bc29f7d4c39d7dd9c2cb9b2faff196f78e269055151f1a2dd57022800 +size 825251488 diff --git a/LFM2.5-1.2B-JP.i1-Q6_K.gguf b/LFM2.5-1.2B-JP.i1-Q6_K.gguf new file mode 100644 index 0000000..3435cb5 --- /dev/null +++ b/LFM2.5-1.2B-JP.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05707e1194d71c1dc28c9a3928346fd5ca5cd55d6ad76cd9a00471929f78cbaf +size 962844320 diff --git a/LFM2.5-1.2B-JP.imatrix.gguf b/LFM2.5-1.2B-JP.imatrix.gguf new file mode 100644 index 0000000..da35fcd --- /dev/null +++ b/LFM2.5-1.2B-JP.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a045d2ef79e66175e4188e19c776774bc455d045204a92f5b7079c0ce24aceb +size 1161536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0abd228 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: LiquidAI/LFM2.5-1.2B-JP +language: +- en +- ja +library_name: transformers +license: other +license_link: LICENSE +license_name: lfm1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- liquid +- lfm2.5 +- edge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-1.2B-JP-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-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/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q2_K.gguf) | i1-Q2_K | 0.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ3_M.gguf) | i1-IQ3_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q4_0.gguf) | i1-Q4_0 | 0.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-JP-i1-GGUF/resolve/main/LFM2.5-1.2B-JP.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +