commit cbff7486f43067d8fe09a62e63e6d823ed8b060e Author: ModelHub XC Date: Thu Jul 9 20:47:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Murasaki-4B-v0.3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cbd12c7 --- /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 +Murasaki-4B-v0.3.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Murasaki-4B-v0.3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Murasaki-4B-v0.3.i1-IQ1_M.gguf b/Murasaki-4B-v0.3.i1-IQ1_M.gguf new file mode 100644 index 0000000..f96a63a --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8612c4b046e7e0c27a9bf82b264ebc5151190e539b288f27020f5cf907137dba +size 1254644480 diff --git a/Murasaki-4B-v0.3.i1-IQ1_S.gguf b/Murasaki-4B-v0.3.i1-IQ1_S.gguf new file mode 100644 index 0000000..33fdda4 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b5c32f3368e29e407a47bf0ba28859e76c0d1303bc30ecb8798a2419a655b3 +size 1182882560 diff --git a/Murasaki-4B-v0.3.i1-IQ2_M.gguf b/Murasaki-4B-v0.3.i1-IQ2_M.gguf new file mode 100644 index 0000000..0befa7c --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07ae71444ecb9d6611a85df5f66164b03f13902751baf41691998a4adda91a1 +size 1680113920 diff --git a/Murasaki-4B-v0.3.i1-IQ2_S.gguf b/Murasaki-4B-v0.3.i1-IQ2_S.gguf new file mode 100644 index 0000000..d907ee2 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8e2d8fedb6664e6fa195d9b0271f6cbb729737628815b563fad58dac3549df +size 1584431360 diff --git a/Murasaki-4B-v0.3.i1-IQ2_XS.gguf b/Murasaki-4B-v0.3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..33b3e0e --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e6e4f94aa7cdda44234afbc3dc5705c458b56e0e9822bef5808b5d613f8d3c +size 1481726720 diff --git a/Murasaki-4B-v0.3.i1-IQ2_XXS.gguf b/Murasaki-4B-v0.3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6b58720 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a695a3626e048fdfc2bcb887151c1a0183396b3bd004a79968b8da079bf4629 +size 1374247680 diff --git a/Murasaki-4B-v0.3.i1-IQ3_M.gguf b/Murasaki-4B-v0.3.i1-IQ3_M.gguf new file mode 100644 index 0000000..ad48543 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c118934331b7168f8d5f69e3387442a5183c842f30399ea5c3cfe6cfd1f811 +size 2130026240 diff --git a/Murasaki-4B-v0.3.i1-IQ3_S.gguf b/Murasaki-4B-v0.3.i1-IQ3_S.gguf new file mode 100644 index 0000000..8e671a9 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b32a3889192d8ef9608039e141e599afa2f30c4baa25453abd29fa885fa5a61 +size 2066661120 diff --git a/Murasaki-4B-v0.3.i1-IQ3_XS.gguf b/Murasaki-4B-v0.3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cf21001 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49316256aefcd49775b8a13ad580cb53a0a1939687401c5da6167181079ad466 +size 1981505280 diff --git a/Murasaki-4B-v0.3.i1-IQ3_XXS.gguf b/Murasaki-4B-v0.3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8118601 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5eb88fce2f44f6974417a3e4aef89636df01047c65c0f75eed453c948acea12 +size 1837318400 diff --git a/Murasaki-4B-v0.3.i1-IQ4_NL.gguf b/Murasaki-4B-v0.3.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f8eb018 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76921edc14f0c1e7fee25bcbf2aeddbae1e0b8dd133d64512f9a90b83966fb45 +size 2600131840 diff --git a/Murasaki-4B-v0.3.i1-IQ4_XS.gguf b/Murasaki-4B-v0.3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3063b48 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8adb1be88c06da3ef49b2df5f54ea66edee0bf1db0875ff39b00bcf830377f6 +size 2477384960 diff --git a/Murasaki-4B-v0.3.i1-Q2_K.gguf b/Murasaki-4B-v0.3.i1-Q2_K.gguf new file mode 100644 index 0000000..a7de3fe --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de70acdb793f6765921de8676edb18fe400dfb7bb429ebd5fa02a26c80a8caa +size 1797126400 diff --git a/Murasaki-4B-v0.3.i1-Q2_K_S.gguf b/Murasaki-4B-v0.3.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9442df6 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55277abe878025e327afc8150c72b88d13daee79f28b80921589eca67eb42499 +size 1691080960 diff --git a/Murasaki-4B-v0.3.i1-Q3_K_L.gguf b/Murasaki-4B-v0.3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..979a0d2 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde114c5bee5e0c3b319076eb3908b8d2251dcc481bb2d204bb6c54e7da18a80 +size 2406915840 diff --git a/Murasaki-4B-v0.3.i1-Q3_K_M.gguf b/Murasaki-4B-v0.3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a4a6faf --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22165e56477815a108239cfffc61ff240fb4aba3ed2adc8ee24fc87fa8c4b328 +size 2242748160 diff --git a/Murasaki-4B-v0.3.i1-Q3_K_S.gguf b/Murasaki-4B-v0.3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..25b7435 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb8578ca7dee9238aea8783d5b2450f54a723fb5d02e3610a9e0a3dc9f8c569 +size 2054127360 diff --git a/Murasaki-4B-v0.3.i1-Q4_0.gguf b/Murasaki-4B-v0.3.i1-Q4_0.gguf new file mode 100644 index 0000000..7855f52 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1c48ad75368c0aea409c637f2bb9179515583bdb710eb9c4de9baac121046a +size 2594561280 diff --git a/Murasaki-4B-v0.3.i1-Q4_1.gguf b/Murasaki-4B-v0.3.i1-Q4_1.gguf new file mode 100644 index 0000000..3036549 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d48619dc502a6871b1c6033f17b18420fee672bc889340cd7bce22850314c9cf +size 2839727360 diff --git a/Murasaki-4B-v0.3.i1-Q4_K_M.gguf b/Murasaki-4B-v0.3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..72c54bd --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:654fe5d0fea323172079dd51d96a15948152c9b3ed2521c2e61c9dd5ec7ceb6e +size 2716069120 diff --git a/Murasaki-4B-v0.3.i1-Q4_K_S.gguf b/Murasaki-4B-v0.3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e83e819 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc35ee7e220ff1f8ad3094c758a220fc1bed6ffe2a8ddea59a5184060229a0ab +size 2602097920 diff --git a/Murasaki-4B-v0.3.i1-Q5_K_M.gguf b/Murasaki-4B-v0.3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..83a1bb9 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d6e570d0c41c657c8388873820aa32149cff79662198ff01834fbca557b9495 +size 3156921600 diff --git a/Murasaki-4B-v0.3.i1-Q5_K_S.gguf b/Murasaki-4B-v0.3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d56acf5 --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d3b822438ef05ef05f3275a15dbe3dad31c290ce4fb305f98051116eb6a5a2 +size 3091119360 diff --git a/Murasaki-4B-v0.3.i1-Q6_K.gguf b/Murasaki-4B-v0.3.i1-Q6_K.gguf new file mode 100644 index 0000000..6db1dce --- /dev/null +++ b/Murasaki-4B-v0.3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8706273a955b3a8a11d2c3412c49cf8daf02f8f45ca2fee4d3b4392787ec8db3 +size 3625327360 diff --git a/Murasaki-4B-v0.3.imatrix.gguf b/Murasaki-4B-v0.3.imatrix.gguf new file mode 100644 index 0000000..ef1f26e --- /dev/null +++ b/Murasaki-4B-v0.3.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e261d503bbbf2b32ddc593f24ae5f336807cee3a6902e87655fd865814b2a965 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b852549 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: Murasaki-Project/Murasaki-4B-v0.3 +language: +- ja +- zh +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- translation +- light-novel +- galgame +- anime-subtitles +- cot +- system-2 +- text-generation-inference +- transformers +- pytorch +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Murasaki-Project/Murasaki-4B-v0.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Murasaki-4B-v0.3-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Murasaki-4B-v0.3-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/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ3_M.gguf) | i1-IQ3_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q4_0.gguf) | i1-Q4_0 | 2.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q4_1.gguf) | i1-Q4_1 | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Murasaki-4B-v0.3-i1-GGUF/resolve/main/Murasaki-4B-v0.3.i1-Q6_K.gguf) | i1-Q6_K | 3.7 | 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. + +