commit 019b0feac3c447051146b1902ecbe223b87e34a9 Author: ModelHub XC Date: Sat Aug 8 03:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b96801b --- /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_Medusa_v1.01.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Medusa_v1.01.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_M.gguf new file mode 100644 index 0000000..18a3825 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdde849776bee9748881460c5c6fa4030fecdfe5399a7390f43d2f9f0b66592 +size 2162140864 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_S.gguf new file mode 100644 index 0000000..dc95d2e --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c193b3db1ca62366fc6942a23f2a75471a442aaa92e9c4da20963f3a5767a77c +size 2019796672 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_M.gguf new file mode 100644 index 0000000..beb88a9 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8faaf0b4af8d815a1e44706295057a2c3b01ae7cf91059b5f48476ed6caaff0 +size 2948466624 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_S.gguf new file mode 100644 index 0000000..4c9245d --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc1cece931a898fd2b32959ce8a77bdda0a5f479f86b8636fa1122d2c2c641e +size 2758674368 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XS.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3dadbc7 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c193367cbc961e06ffc53be8f6e8c3cd6da8b03a9dfa50946e1d81cde8ac5ec4 +size 2605950656 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XXS.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..74f0099 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e080f09260e944a92f1cf3803e783fdfb7fe119225ea7c4db987290da2a973f +size 2399381184 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_M.gguf new file mode 100644 index 0000000..a9e79b9 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcc6a124e52050f29f404a55a12894afa053c60a7d2849de60ad050f3af469a3 +size 3785030848 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_S.gguf new file mode 100644 index 0000000..07ace3d --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5212770957b21bef2622f55b0d9bcee85b2ab2e240b369c79cdcec644321e81 +size 3682532544 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XS.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b9e0c37 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7943e2f46e8f2e957ed949107aa6d6e40d9d669d6045058ee9f650600d7918e +size 3518954688 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XXS.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..595eacc --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:253ae8386032ea623dda3f51bfa806a5706b4c27e0eb49213a2f81ce0c69ffad +size 3275098048 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_NL.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_NL.gguf new file mode 100644 index 0000000..1c4e8f9 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858271df2be23ed6d50c6cce166825c7c665bf7831444ae77b9d0d3956918b5d +size 4678218176 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_XS.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7336b68 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c378d2ae5d44bd1cf55770522d52f2eafb523d3c249b5f2fcb7e687c7cfeac +size 4447886784 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K.gguf new file mode 100644 index 0000000..d9d7bf6 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce070a7e88cd203bd4a9f26668397325d199ddec317fd3946b2abedf01bd12a +size 3179322304 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7f02fa6 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1ff75ddd1e8d92a605ca4b92088ff121cf65e53db144eaa3e24667c24fc5d3 +size 2989005760 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_L.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_L.gguf new file mode 100644 index 0000000..844472d --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e1e32e68939fe0f3abe2051ce5168f3e1cbc6bbbec354447a0bce3dbc507af8 +size 4322163904 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_M.gguf new file mode 100644 index 0000000..53f3fb4 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221d8b6ecdaedd1f3c107e92340014a58a256faddf221d452b9da943855df6ef +size 4019125440 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c09b1df --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d072f057d7efac390b0bcb1be0357f71bfce411337c35d18bfc23c5425222b9e +size 3664706752 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q4_0.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_0.gguf new file mode 100644 index 0000000..c20577c --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949862491e45f4ce9802cfced92a6578b3a2ad48f9012f645fb5e32c1f68d5c9 +size 4676121024 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q4_1.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_1.gguf new file mode 100644 index 0000000..3308e80 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8d3b9a05377165a055e2bd0ecab235dd2998baa7ed4e4b91ced4bf3d7ba4d5 +size 5130492352 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a88f6f4 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb84c2504dcb83be114b3985957999b7c9e2060f005de9df227924f6deb61756 +size 4920963520 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_S.gguf new file mode 100644 index 0000000..07e989d --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93711f8b75f26d4376febe3d7b5266eb357777db8675c18686ef4819deaf9c94 +size 4692898240 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_M.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8cba237 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286aab73fddf7b21099ed5b2c86f152fe35a59202e8c94b8a76615b8b10c52e9 +size 5733237184 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_S.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b79e1a4 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ce99be16195f70c0ef231ace3386b1ffc84d3d3deb7ecf2a643f6f13c642b9 +size 5599543744 diff --git a/Llama_3.1_8b_Medusa_v1.01.i1-Q6_K.gguf b/Llama_3.1_8b_Medusa_v1.01.i1-Q6_K.gguf new file mode 100644 index 0000000..0d6bbd6 --- /dev/null +++ b/Llama_3.1_8b_Medusa_v1.01.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07bfb3d52aac4327af33c2958a967c5cd0403fab5926fe113b8ed190947cd79 +size 6596277952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2cbf40 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Medusa_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_Medusa_v1.01 + + +static quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_v1.01.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Medusa_v1.01-i1-GGUF/resolve/main/Llama_3.1_8b_Medusa_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. + +