commit 29a071b83a8b14ff3158bedf5bfc632e72284518 Author: ModelHub XC Date: Thu Aug 6 13:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a18c5c9 --- /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 +LFM-2.5-1.2b-Instruct-roleplay-tuned.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_M.gguf new file mode 100644 index 0000000..523d4b9 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692b9b50bbf0573592f01890652f201a905cf50077cd6c4e82b0b9c4ee92f9c6 +size 327145696 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_S.gguf new file mode 100644 index 0000000..40bc93d --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9d0f1069a2caca4a3bd493999202592ca2eceeb2656aae2bec92cd2cc8e522 +size 304388320 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_M.gguf new file mode 100644 index 0000000..33788a2 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bb88ac75f9545502a0abeb62ad0dd71adb4d9661681d4e16a5dc586462e85e +size 434133216 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_S.gguf new file mode 100644 index 0000000..8d469b9 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82297f1d5a02b23d2b3c4a13c6dda2b18d6f6faabd5dbfdcff61defe0b66ffe3 +size 403790048 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XS.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XS.gguf new file mode 100644 index 0000000..979aae0 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db2ec37276521cdca5e8191dedd516aa6cd33e28eddb191af45da715b6fcc9b +size 396204256 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3862447 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e68edacd2455672c9354624a04d7d49dcc4e00473ee9e609c1f572ad97cdaa +size 365074656 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_M.gguf new file mode 100644 index 0000000..f7cc9b2 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c21798e017764034715138ca285b80b76bd2c101ee7395f7d33dd04f5d44f8 +size 566794464 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_S.gguf new file mode 100644 index 0000000..b6406aa --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2eb353428daa6c79badc00106fd7f9cee07ad6f9e847f46d252c1b361e943eb +size 558160096 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XS.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d8b40d6 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f00e0f2801853403524b1eec57a78966d2ea910dd4906c8e934b9ca574e445 +size 537811168 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..65f0cb3 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73f4c6967535ad74840c908c46470fefa0891c9e2ca9f8e0c60ce93f08a7c63 +size 490985696 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_NL.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f1a2274 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136cabea1920c2ab0e5a145a6d7988dce61e61daf760272684a2603e7958fca5 +size 695752928 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_XS.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7845f4e --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d413e2de26f68f1734ae576832f8d105d1436e237d86f5856e6643c1d11958bd +size 663378144 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K.gguf new file mode 100644 index 0000000..1caed21 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2420435aced7dcf5f814b406fcc8d291c63fe4d8df8bd4f0900e2da15ab1616 +size 483399904 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4e90743 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266538b6e6711c499a6229e33e07f347eda5c7f68bd6a839f39bed56468171f0 +size 460806368 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_L.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b44dc98 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b40b0de51bfefe245f905c722c8254d9705d984f95525ee3078b8339ee35e56 +size 635476192 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d8aaee7 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ffff609fa578658eba00731230b16a9139b642ad2e7efecca651b5bc9ef113 +size 600348896 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_S.gguf new file mode 100644 index 0000000..86a7762 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b57a4506f1978a6d5e3a5e938bff4ec43785c5538e8257b06be1073402d8c647 +size 558160096 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_0.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_0.gguf new file mode 100644 index 0000000..2b54794 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b572349989e2cd68d3dd309d38bddfbbc881ef78d73beef6731f29f84b3dd6fe +size 697850080 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_1.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_1.gguf new file mode 100644 index 0000000..99f467d --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0959af08ff8dc92d2a62cef2c870bf1e49f18db5155fc343e6e3def9b39b0c2f +size 760502496 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_M.gguf new file mode 100644 index 0000000..07dc159 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd17d764f62758e1505966d4728738df6ed619a32dd37c141f25ef535fea814 +size 730896608 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9c97608 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dae0922f3d9c37acfd89b6a616a4a53bc78bdb6d6d83d74e157c22d57005945 +size 700471520 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_M.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3e5df06 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e934abd9416fc772dccbc109858505046114d23e30a6078398ea1a008d7a2ae +size 843356384 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_S.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_S.gguf new file mode 100644 index 0000000..92f7a7b --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8440cf257fa4c709bf0a81591796da33b0e9e480b866dec38482f5eae88a17d9 +size 825252064 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q6_K.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q6_K.gguf new file mode 100644 index 0000000..5062278 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed01bcb3f45f6487f2c34002f0de596471628798de79efe0f8fee561cd0d0b9b +size 962844896 diff --git a/LFM-2.5-1.2b-Instruct-roleplay-tuned.imatrix.gguf b/LFM-2.5-1.2b-Instruct-roleplay-tuned.imatrix.gguf new file mode 100644 index 0000000..494b4e9 --- /dev/null +++ b/LFM-2.5-1.2b-Instruct-roleplay-tuned.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7c367f1efa41e49c656d2bddb5ba5d9bf8344a6471ed8ca8a1520ec4daf2ad +size 1161536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2712ce --- /dev/null +++ b/README.md @@ -0,0 +1,98 @@ +--- +base_model: Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned +datasets: +- ChaoticNeutrals/Gryphes-Sonnet3.5-Charcard-Roleplay-Heavy_Filtering +language: +- en +library_name: transformers +license: other +license_link: LICENSE +license_name: lfm1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Roleplay +- creative +- lora +- experimental +- finetune +- lfm2.5 +- writer +- rp +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Indexnusrefather/LFM-2.5-1.2b-Instruct-roleplay-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-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/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q2_K.gguf) | i1-Q2_K | 0.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ3_M.gguf) | i1-IQ3_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_0.gguf) | i1-Q4_0 | 0.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM-2.5-1.2b-Instruct-roleplay-tuned-i1-GGUF/resolve/main/LFM-2.5-1.2b-Instruct-roleplay-tuned.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. + +