commit 1d2d6d7ccc299c773893d10fb425a47ebbe0d6af Author: ModelHub XC Date: Thu Aug 6 04:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f310de8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_M.gguf new file mode 100644 index 0000000..fa32da2 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a18cf0c9335bc0a8196c5e692addebd30948986bb088a72f862277d6783807 +size 2162111008 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_S.gguf new file mode 100644 index 0000000..b251c27 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8414030e74b47b9161752bc98c8f4c1386eb27279a3127782c9eb2e40c1b95b0 +size 2019766816 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_M.gguf new file mode 100644 index 0000000..0ca2df1 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dca31a20bae7bc1ed505972b0795861157402f09a762a64103533ac0b827057 +size 2948433440 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_S.gguf new file mode 100644 index 0000000..b2ccd6b --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82be081d77d1661683f4d550ef9a9ad1026dfc0e996ff8e20a061294c065c898 +size 2758641184 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XS.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b1e5e75 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440716b1a9ca872821dc2822c9fb60d07a4fef2edfbb89e11841245d678c966d +size 2605920800 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XXS.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bec3f9d --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4181a23385016d92840aea24ae7efd8b07f4a7a37eb90793e80ce8618cbefdad +size 2399351328 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_M.gguf new file mode 100644 index 0000000..bf995e0 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a76ffe94b849f98a6ff3899a49ef9feffab15bb08c47c079ca8add9642c8e1c +size 3784993312 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_S.gguf new file mode 100644 index 0000000..2665213 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816586a78dd6ac4dd2a8040f55a445c5d07dabd831520011762dda9d9b5d2c78 +size 3682495008 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XS.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d955291 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e56eebf764feb45fbcb7c5fe0e5f631bd4ccb3f5e6ce4fd09e31273619fcbf +size 3518917152 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XXS.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f6a0cf0 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80f196eb76a041cca0d7242832f39a84c43a300b690f0732e5bb7650b9e6e75 +size 3275064864 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_NL.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_NL.gguf new file mode 100644 index 0000000..8a636a7 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:017e1807e236faa0ef3a4a1fefd3ae5c65096d63eff15bb1513b28d0c87ff5ae +size 4678176288 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_XS.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_XS.gguf new file mode 100644 index 0000000..510cbac --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61ecef59d647aae3fb5ce55710f02a7e2a34d70629b2c2012af3a3baf7dac03 +size 4447845920 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K.gguf new file mode 100644 index 0000000..eab1d4d --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8038201835ada7e0ea8cf9de49ec418776db0f6a7a652bbc8c07427b0d10525 +size 3179288096 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7464051 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220c913faf22b1a641da29ae4c168610d2626a58ed81519eb2a0329f7b95a1dd +size 2988971552 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_L.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c586b9c --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83bfba368863a727d3d73500acae1ba132fc1c67f72a9f34494312e62f0ca9c +size 4322126368 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_M.gguf new file mode 100644 index 0000000..bde02b9 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867ccd6dc676b06d80fb0b1289db7e3b9cd3352049b9a2e741391115b469ee4e +size 4019087904 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6939bad --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9878f6e82d0d247b3fee734fdcaf4f4beff0662958735b72eef91be83b1ac75 +size 3664669216 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_0.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_0.gguf new file mode 100644 index 0000000..c0aad92 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2bd25794d482a365b8aeaba8a9e8640c117f89a32b82d533621fc1a6b66fe9 +size 4676079136 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_1.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_1.gguf new file mode 100644 index 0000000..22e6624 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222fd4cc9cf27bd05509c881660d7392abbdf955eda3a8062c1e199c8293469d +size 5130448416 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_M.gguf new file mode 100644 index 0000000..36936ec --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea914b5dbff5aaf14a6eb29446aa077e8ecd5a22fce47e704451a7f7cf0fbd56 +size 4920921632 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_S.gguf new file mode 100644 index 0000000..002360e --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f1c41b196635f257919296de973bd2950aa88acdb351436fa92556823d24be +size 4692856352 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_M.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_M.gguf new file mode 100644 index 0000000..dca79a1 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2316f7f0c59958a21c92e2c8248e3e88e133cfe680d0bea1eb72386a87011130 +size 5733191200 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_S.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3cab99a --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7d66f34c02d2043c966913fb890d753ee362d52a8235c2548c01993c0b8764 +size 5599497760 diff --git a/Llama_3.1_8b_Hermedive_V1.01.i1-Q6_K.gguf b/Llama_3.1_8b_Hermedive_V1.01.i1-Q6_K.gguf new file mode 100644 index 0000000..de5e198 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_V1.01.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8536d08e2682320e568c8d05e8bd519486da32ce4f873dc92dd66d2d9aa88b7c +size 6596227616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..184cf56 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Hermedive_V1.01 +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_Hermedive_V1.01 + + +static quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-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/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_V1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_V1.01.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. + +