commit 4b1a7a8753accc22d4d44a2146c6c8f1b00031f8 Author: ModelHub XC Date: Sun Aug 9 07:03:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..486ebfc --- /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_R1_V1.03.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_M.gguf new file mode 100644 index 0000000..25c3daf --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086769ad32fc605c0f00c8235b25332dbbf0847e55b07da8897df6c5b136acee +size 2161985632 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_S.gguf new file mode 100644 index 0000000..fd229b5 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5685ad6d18cca7404d6a1c8f214c141973c0e6475bcf655ddbcc0fac17c59f +size 2019641440 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_M.gguf new file mode 100644 index 0000000..836c59e --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc239e2aef75ac20ae1acdb1d2c5bd5cdd9759bc02a66a054c07af271265328f +size 2948295584 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_S.gguf new file mode 100644 index 0000000..e760925 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ad87b7b5593d2e9807c4f755e3de6a4f7c66a5b0a704b4095240c9940a5630 +size 2758503328 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b7b266a --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa345c3af227fdfe145b89c6ab516faf5d03d01f6d8dfc3d23f19dac72e69d8 +size 2605795424 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XXS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..325da07 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24dae7e15321196785f4e77dfd8fef1b8d16f774ae1dcfc946fb365eeeabc4de +size 2399225952 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_M.gguf new file mode 100644 index 0000000..f7b1b8d --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd11cabc796fd41cd3f341d7c269c1269fbb1d1fe6ba5eb94a2a7112061d6b2 +size 3784839136 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_S.gguf new file mode 100644 index 0000000..b38c6ce --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c0c5e78bc89f9014240278d3d9b0c00cb51f9c83f6c4d9c98a5d08159888f8 +size 3682340832 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XS.gguf new file mode 100644 index 0000000..62980f0 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e263aa23d03ed36555d4e60f19e4437fa5c13c7db80056180f43e1b921e3d5af +size 3518762976 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XXS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e0fd2c9 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817992ebb300597c91525fb4bc67ad584f7bef7885cb3ebaf402aac3d3cecf84 +size 3274927008 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_NL.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9ab51ea --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1466eed0a7556184d6a6f91ce4f350ad29cb191365dac695bba6e36377068e83 +size 4678005792 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_XS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6630a20 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c094f01a3c64c10ad8d9f651215e6f5f25e4879c32d5e9da009966ac7bcafc42 +size 4447679264 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K.gguf new file mode 100644 index 0000000..0c64641 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12bc2404116f8b24a5feb522121d7eb50b0d509a0b4b472f378f92412dab634 +size 3179146400 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K_S.gguf new file mode 100644 index 0000000..01b31b8 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0544a971f419e155e4d9e8e8d7ac1344cb28727c9b9e34e2671c02bff966b623 +size 2988829856 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_L.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_L.gguf new file mode 100644 index 0000000..743d38d --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe17e978ad4b9b5fab6b0c6219acb9c0ce7f85e22e8b32f6a5d86436ad060552 +size 4321972192 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_M.gguf new file mode 100644 index 0000000..229ef40 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2313129946e1ae851bc6fad1c8a58396711505aeb4885f39b5d570300ee5ed6e +size 4018933728 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1663e0a --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadf40dba9549bcd53256778ada8a691d09459503e83c77941decaf0a5b8d400 +size 3664515040 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_0.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_0.gguf new file mode 100644 index 0000000..384c2e1 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5020ba40f6ceac6627ef2a6178da88635973b35ea3735537edb95efe575e9827 +size 4675908640 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_1.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_1.gguf new file mode 100644 index 0000000..24252f0 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc13dfbd5e49c88af2a6c14ca8f23fc2526baccdedc16242a6f7a6d00af60a19 +size 5130270240 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_M.gguf new file mode 100644 index 0000000..db99e7c --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1258792d28e0b10752e2d7e197dd16b09cafb5c725d5e3479152d588fbf0623 +size 4920751136 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3b2d155 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b198ae0483f6821c91e99de07aa39768bf8fd8112b90405f2e818c9a796b3a +size 4692685856 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_M.gguf new file mode 100644 index 0000000..83aa011 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cac2c7c9a643422100e66de621f475485a11e02d13061414bb7528b3ea010322 +size 5733005344 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d8a6d14 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d5444666146d91fb472c0ba0208362ccaf1e2042f2c81b87668728a90e99e0 +size 5599311904 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q6_K.gguf b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q6_K.gguf new file mode 100644 index 0000000..59533c2 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee6cba5a6a0fa5889eae50cd9098ad2f41887127ce496a153702fc0dc474e14 +size 6596025440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a539ac1 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Hermedive_R1_V1.03 +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_R1_V1.03 + + +static quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-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_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.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_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.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_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.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_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.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_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.03-i1-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.03.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. + +