commit 3d7a11e7fe4d507fca70f133deeb39ef70b3fcf3 Author: ModelHub XC Date: Wed Jun 17 17:17:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fee705c --- /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 +Llama-3.1-8B-FlashNorm.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-FlashNorm.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ1_M.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ1_M.gguf new file mode 100644 index 0000000..b1b3067 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50043f47a9f5d4e7730528e43b44e55ddc01b5196265e83fec01ebb67e376691 +size 2161972864 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ1_S.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ1_S.gguf new file mode 100644 index 0000000..0db2053 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b62e7cdd0b1c78e88a5a449550fc3d8b0fdfeea9cdc7098651942a6bbbd86b +size 2019628672 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ2_M.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ2_M.gguf new file mode 100644 index 0000000..0369bc4 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0460abfe48e54a8390d20be3cf5534e8d5dc0ec404ae558f0298e74a1759aa6b +size 2948281984 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ2_S.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ2_S.gguf new file mode 100644 index 0000000..4c2666b --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e549f189b7fe720dbcb4994db98a4e99ad9435b653831edef693cdd85939926 +size 2758489728 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ2_XS.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b558a04 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c54d44193fa81762ed90c00ffc48330f37e1dad5c30d9a971aaaa63d834328d +size 2605782656 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ2_XXS.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3325199 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c95e4e133108af22b932750bba7e0b1cdf22bfa5ed99f1d8a1d0563b1091180 +size 2399213184 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ3_M.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ3_M.gguf new file mode 100644 index 0000000..a2b6e13 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063ab42c3c154217746b5b7b9a9a9ccc81499faf3df088e6850d3f9a59e3a935 +size 3784824448 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ3_S.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ3_S.gguf new file mode 100644 index 0000000..7a15a40 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57713eca1d4d6af4e22ff1da9022dd19caddd0d745e2b07e77968a5c7436c525 +size 3682326144 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ3_XS.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4ee186c --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fad42dac260dc36ff9a1f29ca2e3d2a60c5e6692b7d58a4e2a5bf3788216460 +size 3518748288 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ3_XXS.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b7e2e81 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af0dae24db37179eb2e32fdfd56dce274f49d89d26f637df8c34fde1121e4b6 +size 3274913408 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ4_NL.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ4_NL.gguf new file mode 100644 index 0000000..75d9207 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0f6492770319fe2b2217696a6eab15fdf4ecd35fff0d2c6e8248aca392ef53 +size 4677990016 diff --git a/Llama-3.1-8B-FlashNorm.i1-IQ4_XS.gguf b/Llama-3.1-8B-FlashNorm.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b0e70eb --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ce8ebae73dd34522b9b24c146a378fc6a93b880c3651b86dc9f7bd7c4f9d49 +size 4447663744 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q2_K.gguf b/Llama-3.1-8B-FlashNorm.i1-Q2_K.gguf new file mode 100644 index 0000000..2b0472e --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db425e1d816fa37cab0368f4f9c7a7a287e15128bb8990b54ec4e7aaf16b55f +size 3179132544 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q2_K_S.gguf b/Llama-3.1-8B-FlashNorm.i1-Q2_K_S.gguf new file mode 100644 index 0000000..55ffc17 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11142dab9f700ce3f0b4a2fa4f0270e076d7442cb869fd36199ac0299025a82d +size 2988816000 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q3_K_L.gguf b/Llama-3.1-8B-FlashNorm.i1-Q3_K_L.gguf new file mode 100644 index 0000000..89ec349 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3077dfc2966a2900af288eae2154e84b9115a1085797138b4727ec6b9af15e80 +size 4321957504 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q3_K_M.gguf b/Llama-3.1-8B-FlashNorm.i1-Q3_K_M.gguf new file mode 100644 index 0000000..372107e --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded4069d40b592169099d1e884a3469e8f4f6e01d0496bafa703e4ec9e6abfa7 +size 4018919040 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q3_K_S.gguf b/Llama-3.1-8B-FlashNorm.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1c76ca2 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7e2e2cc4a71d7b57675c929dbf9ce113bb8c672bbf6d67d013a6b62c020062 +size 3664500352 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q4_0.gguf b/Llama-3.1-8B-FlashNorm.i1-Q4_0.gguf new file mode 100644 index 0000000..1cd0970 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8145a948bebfb34eccd430a10d473832054d173d3d8fe04ec46edba6176fdfd +size 4675892864 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q4_1.gguf b/Llama-3.1-8B-FlashNorm.i1-Q4_1.gguf new file mode 100644 index 0000000..6222206 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52dcbb209a83cc1957a7997ee33d28ecbf9d0fe4925f8fe33e625aefc8adf39 +size 5130253952 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q4_K_M.gguf b/Llama-3.1-8B-FlashNorm.i1-Q4_K_M.gguf new file mode 100644 index 0000000..68c7647 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a65ca941659fad7e59386b4ac46e32fe277b1803a15c339c396195db971fbf7 +size 4920735360 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q4_K_S.gguf b/Llama-3.1-8B-FlashNorm.i1-Q4_K_S.gguf new file mode 100644 index 0000000..895a9fb --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd6f32866c5b5d3b7e25a2e881a5e648a48be9b332be373e701aed30b62abd3 +size 4692670080 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q5_K_M.gguf b/Llama-3.1-8B-FlashNorm.i1-Q5_K_M.gguf new file mode 100644 index 0000000..906196c --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c53fbd2cdb301aab4d112f4baa45c8beb4d52519c966e2aeec89afaf2ecd6bf +size 5732988544 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q5_K_S.gguf b/Llama-3.1-8B-FlashNorm.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b017316 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaa96030fe93d21db047d5e7d84daa9f73dfbfd46e0bb1a7d79af692503610c +size 5599295104 diff --git a/Llama-3.1-8B-FlashNorm.i1-Q6_K.gguf b/Llama-3.1-8B-FlashNorm.i1-Q6_K.gguf new file mode 100644 index 0000000..1bad232 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8950332a844ec3522156f00edccbc433dc234b9c4c1bbcbb09b021a176d1c03f +size 6596007552 diff --git a/Llama-3.1-8B-FlashNorm.imatrix.gguf b/Llama-3.1-8B-FlashNorm.imatrix.gguf new file mode 100644 index 0000000..af31de0 --- /dev/null +++ b/Llama-3.1-8B-FlashNorm.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71766e69e6c51a0fbd3295c5511a3d533fe7c37fdb6abf49a2759b8154372400 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ba53604 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: open-machine/Llama-3.1-8B-FlashNorm-test +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- flashnorm +- transformer-tricks +- efficient-inference +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/open-machine/Llama-3.1-8B-FlashNorm-test + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-FlashNorm-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-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-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-FlashNorm-i1-GGUF/resolve/main/Llama-3.1-8B-FlashNorm.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. + +