commit 14776d031bfb0251f3a0e4cd6da11d8dc0156316 Author: ModelHub XC Date: Wed May 20 02:00:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cece99f --- /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 +MAGIC-Llama3.1-8B-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MAGIC-Llama3.1-8B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..d6712d7 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31a196c8c5a581cb510ad28d1be97df3da191c59fca3d00b3f9af4b004a269b +size 2161977152 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..924462b --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10fed05aa9726bcbd4cda62c9b42dc665bfc558d619979c5b9fc758f5d51310 +size 2019632960 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..ca7debc --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9de87cf51a0f536e07ef431ec840748886ccd6ef05aac8b6d1cf62ca8115d68 +size 2948286272 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..e21bd72 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43ae9a75956d178e7a2bee09bf003157a6deecea468b25a1e22183233a1f340 +size 2758494016 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XS.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5cd905e --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5e05317ab42f94dd3f7914daf8d7eb7652aeb575d079073781af759f3f8255 +size 2605786944 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XXS.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7086a6c --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eefc6d4662fc38030e54f2a7e76bc2c9f16490f615a5e647535709a4bd6c828 +size 2399217472 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..e379989 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd2d8648377996590fda4d4ad14c4c382cb23975765833f496945f01fe2718a +size 3784828736 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..83e7032 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68be75ddc74d602800d6eaa7eaf21c2c9614bb18d1732be50c7ec7d42cab1912 +size 3682330432 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XS.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ee94d40 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0123f23b8b404568edfb383259eb74e427cd2a4b874f4d5eb3c9cb9cb017d1e +size 3518752576 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XXS.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..62b7e55 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33058420e926598449ee3f594423080de504329864541066308d66db5b0ae592 +size 3274917696 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_NL.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5df430d --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a538b41f20e9311b94cd6a00ab986447a1591a29d4c733eb7c4ae24727b75b83 +size 4677994304 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_XS.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5c26ba8 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2fe7b16430767ceb1c3694e155ee8ccff1ee13372a2b90320ed91cc94eebd9 +size 4447668032 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..8f9ecc2 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af8ed69a794b91be79edb52788368bf8911a5e76b4b8cd10703fe8b2cf1bf69 +size 3179136832 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0f578be --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5d9936defc07093cc3bc6e1e64c719a4e4678e9dc4a98a8512ffafdbd42eb8 +size 2988820288 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_L.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..450496a --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0914fd3cfd0cfa783671bf75cfe3d5f9f42253c52b0d8aa26699e87cd03d11b6 +size 4321961792 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..16bc6c6 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0dbf82d15f67fae6a6feaa8be91315bb2103fe7795025749007ce137c1baa9c +size 4018923328 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..81eb7e7 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220606d5227f16314d46c13c717099036b7e535730d6e1bd548be12376bc3276 +size 3664504640 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q4_0.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..8db2c11 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c51fea17190a05d69405622e51c3741a7f51476a7968a0b7c04dab1fe48f38e +size 4675897152 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q4_1.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..37aa385 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cdc9059e8abc42114352452fcc393339b26a4a0c511633f8edd2f87e6cccab1 +size 5130258240 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..089d1c5 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a180ac166c5abec6ae353c2392cea042fc7c76b8d5636fccd386d2de5aa70498 +size 4920739648 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b1fc889 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e2a91425ba953336dafb5e2ab9f090f33af20547546caf72516cbfcfcaaa12 +size 4692674368 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_M.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e32e820 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59be96a73c318caf635e71ea06d16e85f8f698a089fa8769541d64564dadd3e +size 5732992832 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_S.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..dd4cd51 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fea6ada73bb68f794dee36fd6455da2ab784f1e1ab443f5fe011e7122e24181 +size 5599299392 diff --git a/MAGIC-Llama3.1-8B-Instruct.i1-Q6_K.gguf b/MAGIC-Llama3.1-8B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..1a5eba8 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad33d9a8f8adcaa2391987a69421cf7a0f8243496dd88db64c3657196298b8c9 +size 6596011840 diff --git a/MAGIC-Llama3.1-8B-Instruct.imatrix.gguf b/MAGIC-Llama3.1-8B-Instruct.imatrix.gguf new file mode 100644 index 0000000..42fd5a3 --- /dev/null +++ b/MAGIC-Llama3.1-8B-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b578cb43a66ad416eeb368a2e24281032eca3ae51fdd30dac92090430334979a +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..521158d --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: XiaoyuWen/MAGIC-Llama3.1-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- safety +- alignment +- adversarial-training +- red-teaming +- defense +- large-language-model +- llm-safety +- huggingface +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/XiaoyuWen/MAGIC-Llama3.1-8B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MAGIC-Llama3.1-8B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-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/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MAGIC-Llama3.1-8B-Instruct-i1-GGUF/resolve/main/MAGIC-Llama3.1-8B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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. + +