commit 54a6e3c1f9ac3b5beed31e830fcde82e445678ee Author: ModelHub XC Date: Tue May 12 04:10:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Loxa-1.6B-uncensored-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ab7de3 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Loxa-1.6B-uncensored.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Loxa-1.6B-uncensored.i1-IQ1_M.gguf b/Loxa-1.6B-uncensored.i1-IQ1_M.gguf new file mode 100644 index 0000000..22dfbad --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b961be81516612e1a5143ff65bbb2d1b36a570a9daadf2d4941980ff2f0b3bd +size 510522272 diff --git a/Loxa-1.6B-uncensored.i1-IQ1_S.gguf b/Loxa-1.6B-uncensored.i1-IQ1_S.gguf new file mode 100644 index 0000000..2b2735a --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327f4cd7775b8256450a00e174bea39fcfbaeb800517a1fe27af988b8d076193 +size 481350560 diff --git a/Loxa-1.6B-uncensored.i1-IQ2_M.gguf b/Loxa-1.6B-uncensored.i1-IQ2_M.gguf new file mode 100644 index 0000000..8027dca --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac6038494a99937b2e080112cd49a1940132456973f0955987fbc7e8e8f6ef8 +size 656921504 diff --git a/Loxa-1.6B-uncensored.i1-IQ2_S.gguf b/Loxa-1.6B-uncensored.i1-IQ2_S.gguf new file mode 100644 index 0000000..064e53f --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3bc1541d5d42fad8911f9bfc4d4ef654c3b125a5b9fc092750b924593015776 +size 618025888 diff --git a/Loxa-1.6B-uncensored.i1-IQ2_XS.gguf b/Loxa-1.6B-uncensored.i1-IQ2_XS.gguf new file mode 100644 index 0000000..88cb85b --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce9c7c9e5984d666ec3a656ad0568dbb76d5b4e917aa1c7e92e4feabb38a149 +size 601052064 diff --git a/Loxa-1.6B-uncensored.i1-IQ2_XXS.gguf b/Loxa-1.6B-uncensored.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ca38024 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beed63e04de3fdf072e594f1ba2bc1fd3b926e680f4e54ec1e018c0f23da736b +size 559141792 diff --git a/Loxa-1.6B-uncensored.i1-IQ3_M.gguf b/Loxa-1.6B-uncensored.i1-IQ3_M.gguf new file mode 100644 index 0000000..6ccc836 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a02a7511e53219a5a54bbf85f1a6f7a4f572c56d4b9518a3066a1b1f462ebbd +size 845210528 diff --git a/Loxa-1.6B-uncensored.i1-IQ3_S.gguf b/Loxa-1.6B-uncensored.i1-IQ3_S.gguf new file mode 100644 index 0000000..c882fae --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd548be6f7c284cfd312aff4899e09f9a1e2228bfe66c66bbde6cd6580a2a74 +size 827941792 diff --git a/Loxa-1.6B-uncensored.i1-IQ3_XS.gguf b/Loxa-1.6B-uncensored.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5b0bb41 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783e34a4271c7ab7e355127e55d0c713c1832526373c5860592c4af59420de89 +size 793977760 diff --git a/Loxa-1.6B-uncensored.i1-IQ3_XXS.gguf b/Loxa-1.6B-uncensored.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c129bb4 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74fe23a116510eee79b9d8ebd292c805f1e679e48062b95c091bcf96dedcc683 +size 725603232 diff --git a/Loxa-1.6B-uncensored.i1-IQ4_NL.gguf b/Loxa-1.6B-uncensored.i1-IQ4_NL.gguf new file mode 100644 index 0000000..81b1fa4 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc0e841d0703b8e9726b7364ee2149b7bf5b5722cb2ca791a511b7a6c561a5f +size 1013531552 diff --git a/Loxa-1.6B-uncensored.i1-IQ4_XS.gguf b/Loxa-1.6B-uncensored.i1-IQ4_XS.gguf new file mode 100644 index 0000000..00451d0 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8115048a60dd66a9fc251fbddde5d1c28d874032d67e7c5839506ed386333d14 +size 970572704 diff --git a/Loxa-1.6B-uncensored.i1-Q2_K.gguf b/Loxa-1.6B-uncensored.i1-Q2_K.gguf new file mode 100644 index 0000000..945b2a9 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033dad02b784b6321a2bcee5aa23dbaec943ed58ae11df202f7499cca28963f5 +size 737313696 diff --git a/Loxa-1.6B-uncensored.i1-Q2_K_S.gguf b/Loxa-1.6B-uncensored.i1-Q2_K_S.gguf new file mode 100644 index 0000000..09829a7 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341c4fd1121a36bd022dc2ffd532ff78464bb20173dd4b581047f6281d5cd292 +size 696189856 diff --git a/Loxa-1.6B-uncensored.i1-Q3_K_L.gguf b/Loxa-1.6B-uncensored.i1-Q3_K_L.gguf new file mode 100644 index 0000000..398609b --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9abdde7caf22e6c4c0f975e69606335c0458ab96d30139becfa1e50a74f208e +size 955311008 diff --git a/Loxa-1.6B-uncensored.i1-Q3_K_M.gguf b/Loxa-1.6B-uncensored.i1-Q3_K_M.gguf new file mode 100644 index 0000000..77ab51b --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da68e385d01a8ec7f3ebd9c89352e5af242e4bc602a03afc2a231aeb4cd4b51 +size 894362528 diff --git a/Loxa-1.6B-uncensored.i1-Q3_K_S.gguf b/Loxa-1.6B-uncensored.i1-Q3_K_S.gguf new file mode 100644 index 0000000..acdaf7a --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fbabc2c9d59cbd3bd91f960b3a9144b8a8d4e2c8f0da414f88faded9f3065cc +size 824738720 diff --git a/Loxa-1.6B-uncensored.i1-Q4_0.gguf b/Loxa-1.6B-uncensored.i1-Q4_0.gguf new file mode 100644 index 0000000..7e5ac98 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5002f31b603c5fcb5d3ade67e2ef6d82c520dceb84f0cf727668167e87912b12 +size 1012614048 diff --git a/Loxa-1.6B-uncensored.i1-Q4_1.gguf b/Loxa-1.6B-uncensored.i1-Q4_1.gguf new file mode 100644 index 0000000..c2dc943 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c534687b621633ad1851128c6f961326ddc4bfe60c69736031dae08a9e35d9 +size 1097941920 diff --git a/Loxa-1.6B-uncensored.i1-Q4_K_M.gguf b/Loxa-1.6B-uncensored.i1-Q4_K_M.gguf new file mode 100644 index 0000000..397874e --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804c2c34dffd7b0a67be72d629393293896001b1edde1634187d1c7c9f6d988b +size 1061069728 diff --git a/Loxa-1.6B-uncensored.i1-Q4_K_S.gguf b/Loxa-1.6B-uncensored.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ed7db97 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b798d77ce98a3341292031858a02bdbcfd2990f1318789e7043c826f5b1da701 +size 1015235488 diff --git a/Loxa-1.6B-uncensored.i1-Q5_K_M.gguf b/Loxa-1.6B-uncensored.i1-Q5_K_M.gguf new file mode 100644 index 0000000..28a8ce7 --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1322a6c736817deb2227cb115f5ec8edf2d5cba02795952e6dd0c8e89e685b5b +size 1211409312 diff --git a/Loxa-1.6B-uncensored.i1-Q5_K_S.gguf b/Loxa-1.6B-uncensored.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fc61acf --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e1d21abefeed205bd9b99f7186962e58002fbe6bb361f295eaa882a78421fa +size 1185366944 diff --git a/Loxa-1.6B-uncensored.i1-Q6_K.gguf b/Loxa-1.6B-uncensored.i1-Q6_K.gguf new file mode 100644 index 0000000..382d5df --- /dev/null +++ b/Loxa-1.6B-uncensored.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79dc9663622f810d3dc8a0168f6ee9371cd0f38988a13e1d6acf2b4a7f82693a +size 1371145120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec100ef --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: frameai/Loxa-1.6B-uncensored +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- cpu +- gpu +- aiframe +- Loxa +- conversational +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/frameai/Loxa-1.6B-uncensored + + +static quants are available at https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-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/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 1.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Loxa-1.6B-uncensored-i1-GGUF/resolve/main/Loxa-1.6B-uncensored.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..870abe1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a7e3c20aa27468fbc2141b5ed094b39af98380ffb63d9accb59b59e9659a90a +size 1889484