commit a409c57fb98f8711991cfc4a42dd09c322603d2b Author: ModelHub XC Date: Thu Jun 18 06:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PLLuM-4B-instruct-2512-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41faa6f --- /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 +PLLuM-4B-instruct-2512.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-instruct-2512.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLLuM-4B-instruct-2512.i1-IQ1_M.gguf b/PLLuM-4B-instruct-2512.i1-IQ1_M.gguf new file mode 100644 index 0000000..9d04867 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6a7e9c8935be7e977026d0d2605786e916f9238235fac0e8fac829a066eeb3 +size 1199462016 diff --git a/PLLuM-4B-instruct-2512.i1-IQ1_S.gguf b/PLLuM-4B-instruct-2512.i1-IQ1_S.gguf new file mode 100644 index 0000000..4efc650 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:140f3ce47cd9df81089c0f4f902c8f9ed40f400beb9a2a6b576506429dfc2437 +size 1132983936 diff --git a/PLLuM-4B-instruct-2512.i1-IQ2_M.gguf b/PLLuM-4B-instruct-2512.i1-IQ2_M.gguf new file mode 100644 index 0000000..d5e0cc5 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c4a213ede6c3ea0fd5e120afcb03641848c180b18d3f1165f0665a0debcd91 +size 1537873536 diff --git a/PLLuM-4B-instruct-2512.i1-IQ2_S.gguf b/PLLuM-4B-instruct-2512.i1-IQ2_S.gguf new file mode 100644 index 0000000..dda465c --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c12ae70ce9d3d073f825abbe51c699fec4363f05a53510e7cd3d721e09c81f4 +size 1449236096 diff --git a/PLLuM-4B-instruct-2512.i1-IQ2_XS.gguf b/PLLuM-4B-instruct-2512.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e44e137 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f875728a6140c2c6d9bc00f9ac3f0dd2deacefa3a6fb96516caf57636e10a28 +size 1404466816 diff --git a/PLLuM-4B-instruct-2512.i1-IQ2_XXS.gguf b/PLLuM-4B-instruct-2512.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..2fd4789 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d80841c647f758817b6db67668306ff00bbf8f5e309cfd91676d25924b4e9da +size 1310258816 diff --git a/PLLuM-4B-instruct-2512.i1-IQ3_M.gguf b/PLLuM-4B-instruct-2512.i1-IQ3_M.gguf new file mode 100644 index 0000000..d088d31 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92620d06458839bc21c45634a869afbf4a2f33ba241a7c5875fc26f0f86d46b9 +size 1986673280 diff --git a/PLLuM-4B-instruct-2512.i1-IQ3_S.gguf b/PLLuM-4B-instruct-2512.i1-IQ3_S.gguf new file mode 100644 index 0000000..813c625 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12af4cb5f003cb4eeb1f19bb55b116a02a2863a07e488fdb07573cfaf0fd61bf +size 1937234560 diff --git a/PLLuM-4B-instruct-2512.i1-IQ3_XS.gguf b/PLLuM-4B-instruct-2512.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2b4a288 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9058b7dbc12c747cf1135cd9f78140a7b9bf8fa99880fa5024644549f2e8e74 +size 1863260800 diff --git a/PLLuM-4B-instruct-2512.i1-IQ3_XXS.gguf b/PLLuM-4B-instruct-2512.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8475674 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8337fed4b4d622f24003a1de81e04754d62fc5e4aaabe11d6e26a6cf6cbc8e +size 1689343616 diff --git a/PLLuM-4B-instruct-2512.i1-IQ4_NL.gguf b/PLLuM-4B-instruct-2512.i1-IQ4_NL.gguf new file mode 100644 index 0000000..b48b56e --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ab4a34e55bdddb08de55713499136579a4515b3ec3049a889f3a9c63b8d9c1 +size 2363382400 diff --git a/PLLuM-4B-instruct-2512.i1-IQ4_XS.gguf b/PLLuM-4B-instruct-2512.i1-IQ4_XS.gguf new file mode 100644 index 0000000..574c712 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125ed3b9c392eb20271fd9711b189d2908564e26e0d17bc1cd605f5e2fd906fc +size 2263112320 diff --git a/PLLuM-4B-instruct-2512.i1-Q2_K.gguf b/PLLuM-4B-instruct-2512.i1-Q2_K.gguf new file mode 100644 index 0000000..5e1c3ef --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f68ade9f9c9318d01da1e3ad45996325ad548b68f7227bcb2fab8494fcc4c48 +size 1729034880 diff --git a/PLLuM-4B-instruct-2512.i1-Q2_K_S.gguf b/PLLuM-4B-instruct-2512.i1-Q2_K_S.gguf new file mode 100644 index 0000000..56bc055 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd88c9b49f576615e1d928498a59dad1e44d7464ba88c5fcc028e2587a658dc +size 1635932800 diff --git a/PLLuM-4B-instruct-2512.i1-Q3_K_L.gguf b/PLLuM-4B-instruct-2512.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f49ffc8 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edec61eab267b0ca95aef72da57c5e1e7b702754a3554cd51951840352da86f1 +size 2235955840 diff --git a/PLLuM-4B-instruct-2512.i1-Q3_K_M.gguf b/PLLuM-4B-instruct-2512.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cfd0a2c --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b27b22c2893a568e1f23c6ec5f0a14321f0980a4512d7579295215659201fcd +size 2098330240 diff --git a/PLLuM-4B-instruct-2512.i1-Q3_K_S.gguf b/PLLuM-4B-instruct-2512.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1874587 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2da6068da1f80c96a299a50cbae61afe292ee251dcbff692e1e9dfcb4eecc2 +size 1937234560 diff --git a/PLLuM-4B-instruct-2512.i1-Q4_0.gguf b/PLLuM-4B-instruct-2512.i1-Q4_0.gguf new file mode 100644 index 0000000..e8453e6 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170dba40a1194becb435aad2813a9afa1266ec4498da9bdb912bf0837c691d21 +size 2369936000 diff --git a/PLLuM-4B-instruct-2512.i1-Q4_1.gguf b/PLLuM-4B-instruct-2512.i1-Q4_1.gguf new file mode 100644 index 0000000..a052038 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ed1b3fa46bc04548f5149c33966211abf590eac83aec32eb0768acf0f20641 +size 2563922560 diff --git a/PLLuM-4B-instruct-2512.i1-Q4_K_M.gguf b/PLLuM-4B-instruct-2512.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c96c213 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d6e27b05d96392eae30ea19e20767d6746ed884e1af322a41f76c032c5db6f +size 2489764480 diff --git a/PLLuM-4B-instruct-2512.i1-Q4_K_S.gguf b/PLLuM-4B-instruct-2512.i1-Q4_K_S.gguf new file mode 100644 index 0000000..f20d878 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0949b867c9b5b8850d742a4544838e189c6eae4a8ef6d4a4e05c280d6b5eb8 +size 2377800320 diff --git a/PLLuM-4B-instruct-2512.i1-Q5_K_M.gguf b/PLLuM-4B-instruct-2512.i1-Q5_K_M.gguf new file mode 100644 index 0000000..167c42e --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87ba571886d86c7e824afb957d3cd60bc4aa78eb85c39d5f2a7e1682a1fdb348 +size 2829568640 diff --git a/PLLuM-4B-instruct-2512.i1-Q5_K_S.gguf b/PLLuM-4B-instruct-2512.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e2efb63 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c3f292b6b80d0495b0e35f73aea7fcda4e87f1ec34dcae1c6d6b8aa251854a +size 2764462720 diff --git a/PLLuM-4B-instruct-2512.i1-Q6_K.gguf b/PLLuM-4B-instruct-2512.i1-Q6_K.gguf new file mode 100644 index 0000000..2574674 --- /dev/null +++ b/PLLuM-4B-instruct-2512.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2018090ecfdd44963446ef9135079d07fdcf2dc781e89925ec87af8d99ca28d8 +size 3190610560 diff --git a/PLLuM-4B-instruct-2512.imatrix.gguf b/PLLuM-4B-instruct-2512.imatrix.gguf new file mode 100644 index 0000000..3d162ed --- /dev/null +++ b/PLLuM-4B-instruct-2512.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6e23d06a31c9a2c577b1ead57894478253c2429aaa138883aa0492ca9612d0 +size 3448608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..afaba89 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: CYFRAGOVPL/PLLuM-4B-instruct-2512 +language: +- pl +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/CYFRAGOVPL/PLLuM-4B-instruct-2512 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-4B-instruct-2512-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-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/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ1_M.gguf) | i1-IQ1_M | 1.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-instruct-2512-i1-GGUF/resolve/main/PLLuM-4B-instruct-2512.i1-Q6_K.gguf) | i1-Q6_K | 3.3 | 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. + +