commit 68072c0fdc8d3e524c8fb7b2e168dd362359dc92 Author: ModelHub XC Date: Wed Jun 3 22:42:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65803a9 --- /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-Queen-8B-A1B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ1_M.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ1_M.gguf new file mode 100644 index 0000000..2e7d659 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac678585e1fd7b2645719bc841f7a8a023f1bc3b8f2df6d2a25701c782460ba +size 2008920000 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ1_S.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ1_S.gguf new file mode 100644 index 0000000..9bf1a1e --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0edc26e9f39d21a379354199054ca926b7f2433ba7247956177ee18293da16 +size 1820815296 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ2_M.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ2_M.gguf new file mode 100644 index 0000000..05dfab6 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f691b0ea7c3057ec57fa4bfb9db447d2aecc2d333d1e6e28f1335244ac53e67 +size 2843275200 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ2_S.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ2_S.gguf new file mode 100644 index 0000000..2949ea4 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dadd6a9bf8aebeefee6e760bce81ddc2d3cd9c613a28647ac8b36a3155f9878 +size 2592468928 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ2_XS.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..21ffc11 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd152b7909776cd67d6b6754f4ef48e1b71362477ccb757235bdc83c87c9f30 +size 2574020544 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ2_XXS.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7d1af65 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b8566f2e6707818dafe5a00c79cd2bb059652b1d8135db2556149784cefe52c +size 2322427840 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ3_M.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ3_M.gguf new file mode 100644 index 0000000..fb20e3f --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263c4f3b953ca9b1dff1d20495cb404cbb7d5d6939b3ec264f97141e4174fa38 +size 3778752448 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ3_S.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ3_S.gguf new file mode 100644 index 0000000..459f541 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1c9488d4f12264e51d3506dc4046ba8b63682682bb6149acbe3dae57d1e585 +size 3755077568 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ3_XS.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b062f38 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e80be687a761be45e50709bafb90c596e582fc849ba4396dfa30e9e9f8b5bc9 +size 3555422144 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ3_XXS.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..39295a2 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85245826a7e4047b731b545a3db9f2ebd183a4616d008c500e67952b4cd9b87f +size 3334909888 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ4_NL.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f569695 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35d4083d55ea0de59b6dfc0542fc30bda9f8699b70c354e18878732f29c29eb +size 4844679104 diff --git a/LFM2.5-Queen-8B-A1B.i1-IQ4_XS.gguf b/LFM2.5-Queen-8B-A1B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..226abe0 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3059e8bd31b76ccff1177ccbf1eed37a11484db3af193dfd72a723422d2e3b3 +size 4588302272 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q2_K.gguf b/LFM2.5-Queen-8B-A1B.i1-Q2_K.gguf new file mode 100644 index 0000000..f6dc4c7 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9f32355ebd11c33ca90e309afd386f93ce15ee710a43d150fc9b1e24fd7c8a +size 3190435776 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q2_K_S.gguf b/LFM2.5-Queen-8B-A1B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7481e10 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f84c646fb80ea5f3960616bd70734bf31016faa9161acf583e639ff12b18da1 +size 2956259264 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q3_K_L.gguf b/LFM2.5-Queen-8B-A1B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b86b66d --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a5dee144036d2ac0495e090d703dcae9e5df17656007c690dec63f7f25e45d +size 4436864960 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q3_K_M.gguf b/LFM2.5-Queen-8B-A1B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..51e0a32 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37db8ed0b49274213fca9d112cad8597dfe5bae06c5fb389ef99c3e7980d959 +size 4108398528 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q3_K_S.gguf b/LFM2.5-Queen-8B-A1B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b193811 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442b8fa272a6a87a0d1b1d9703b7eecb75b9b3839355426cedb8ec27b4717700 +size 3755077568 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q4_0.gguf b/LFM2.5-Queen-8B-A1B.i1-Q4_0.gguf new file mode 100644 index 0000000..3076d96 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2cbaef3736169add9ee1bcbad24c6962d5b95579763a479a1d38c23a66aee18 +size 4853854144 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q4_1.gguf b/LFM2.5-Queen-8B-A1B.i1-Q4_1.gguf new file mode 100644 index 0000000..1f3d8f8 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bfedd69779b7444a3787b3ceec00381b6c7a42d887849808af9ab73523e0dde +size 5357432768 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q4_K_M.gguf b/LFM2.5-Queen-8B-A1B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..14ed77d --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a84de2480c14605c7b867cd6dbadf62148cd7bee2273df2dacf45e9a25151b9 +size 5155565504 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q4_K_S.gguf b/LFM2.5-Queen-8B-A1B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fab38c1 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c95575c3328b9fccecded5c9e78db584dafa6b3f2e735de0ae6c54b024b4796 +size 4863553472 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q5_K_M.gguf b/LFM2.5-Queen-8B-A1B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..157b499 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c84a06a14953a416f15de2349009b0c71a8f9176be85bbdfdfebaeb6a09e1a16 +size 6030340032 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q5_K_S.gguf b/LFM2.5-Queen-8B-A1B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..69c9a27 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e579eab5b095cf404777bebe3016b603e7c38e7aeda1b118bb270d0d43299f8 +size 5870186432 diff --git a/LFM2.5-Queen-8B-A1B.i1-Q6_K.gguf b/LFM2.5-Queen-8B-A1B.i1-Q6_K.gguf new file mode 100644 index 0000000..ee2e06e --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abfc26b96a9c1b6e833ee39d7fd5b5929b4dadedbe393e636e4121d318928163 +size 6959787968 diff --git a/LFM2.5-Queen-8B-A1B.imatrix.gguf b/LFM2.5-Queen-8B-A1B.imatrix.gguf new file mode 100644 index 0000000..bff5a8b --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e994aeb9014de3beb45e5e658f57b353f26de61718d43f2a727c86e3a3a92934 +size 17375200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d3bf51 --- /dev/null +++ b/README.md @@ -0,0 +1,99 @@ +--- +base_model: aifeifei798/LFM2.5-Queen-8B-A1B +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +- pt +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/aifeifei798/LFM2.5-Queen-8B-A1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-Queen-8B-A1B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-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-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q4_0.gguf) | i1-Q4_0 | 5.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q4_1.gguf) | i1-Q4_1 | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.i1-Q6_K.gguf) | i1-Q6_K | 7.1 | 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. + +