commit 9d6c6443b4ef4aac30b54d6d4856ccca896dee08 Author: ModelHub XC Date: Sat Jun 27 15:21:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-ScaleQuest-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..330df17 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-ScaleQuest.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-ScaleQuest.i1-IQ1_M.gguf b/Llama3-8B-ScaleQuest.i1-IQ1_M.gguf new file mode 100644 index 0000000..3b10063 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc0bb215616e3524eca45bf036a6e31e2b04e99ab5053ce36bf46669464b545 +size 2162239936 diff --git a/Llama3-8B-ScaleQuest.i1-IQ1_S.gguf b/Llama3-8B-ScaleQuest.i1-IQ1_S.gguf new file mode 100644 index 0000000..2f7ec15 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e21071497436072c6a44a6bd61a5cd004ada19bfb3009906c6c718e17eebebfc +size 2019895744 diff --git a/Llama3-8B-ScaleQuest.i1-IQ2_M.gguf b/Llama3-8B-ScaleQuest.i1-IQ2_M.gguf new file mode 100644 index 0000000..4040951 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29fdc1739d9484409dafe8607ffca2fad6262b46d7745ff61dc974d3bbc18a4f +size 2948575680 diff --git a/Llama3-8B-ScaleQuest.i1-IQ2_S.gguf b/Llama3-8B-ScaleQuest.i1-IQ2_S.gguf new file mode 100644 index 0000000..2298933 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fbfecdfc2a4818204c0e62206d27b0f4b08a7730ccfe63a9fd747f47a9f8d7 +size 2758783424 diff --git a/Llama3-8B-ScaleQuest.i1-IQ2_XS.gguf b/Llama3-8B-ScaleQuest.i1-IQ2_XS.gguf new file mode 100644 index 0000000..18dc71d --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd50c0ccb62a28b37b7341dab46ed82edb44e1a4fd330f1360b5e18dd465733b +size 2606049728 diff --git a/Llama3-8B-ScaleQuest.i1-IQ2_XXS.gguf b/Llama3-8B-ScaleQuest.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e6a96b3 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54ab738a57e402c7526f139d20dccb3a2dd72cd0807e8928a1da2c28e0ebb52 +size 2399480256 diff --git a/Llama3-8B-ScaleQuest.i1-IQ3_M.gguf b/Llama3-8B-ScaleQuest.i1-IQ3_M.gguf new file mode 100644 index 0000000..258cfd2 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cd2396627ac90203463a484e7859dc03c0edc2202e8210cebe82cfb8e4471b +size 3785152960 diff --git a/Llama3-8B-ScaleQuest.i1-IQ3_S.gguf b/Llama3-8B-ScaleQuest.i1-IQ3_S.gguf new file mode 100644 index 0000000..6295850 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52eabfb9b2f65a9e22d36fe66fbde32b8d9a62e571c33a74cc5cc5ac6f66ea3f +size 3682654656 diff --git a/Llama3-8B-ScaleQuest.i1-IQ3_XS.gguf b/Llama3-8B-ScaleQuest.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1051070 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a5f3bb00ef002bf0b7e5aa81cbdd365ce9aec0549cad1033e0a7a3abd6b7aa +size 3519076800 diff --git a/Llama3-8B-ScaleQuest.i1-IQ3_XXS.gguf b/Llama3-8B-ScaleQuest.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f455d8a --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b4e389d3d24e836c0dafffeb5046cf4f0c088add709ebf34fba7bc356f1f6d +size 3275207104 diff --git a/Llama3-8B-ScaleQuest.i1-IQ4_XS.gguf b/Llama3-8B-ScaleQuest.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6a46290 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ec54c9ec9c4f2ad09dce75b6980fe2406afda13c3285cbd87f2e6c7a6c671f +size 4448018880 diff --git a/Llama3-8B-ScaleQuest.i1-Q2_K.gguf b/Llama3-8B-ScaleQuest.i1-Q2_K.gguf new file mode 100644 index 0000000..da8e88e --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f24d8ef6e11bfd4e65427256e593c1896028f935a3ca52249a186cb171604b +size 3179434432 diff --git a/Llama3-8B-ScaleQuest.i1-Q3_K_L.gguf b/Llama3-8B-ScaleQuest.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4884eff --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c180501f77dbcc7860cef9b4a00c80111d396a0e24f2a96b30d536a29f7aa09 +size 4322286016 diff --git a/Llama3-8B-ScaleQuest.i1-Q3_K_M.gguf b/Llama3-8B-ScaleQuest.i1-Q3_K_M.gguf new file mode 100644 index 0000000..708c304 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b996d4d2a030cb1e37d632e1a0a160b3f906913f60b00dbbdb9a113de8440ee +size 4019247552 diff --git a/Llama3-8B-ScaleQuest.i1-Q3_K_S.gguf b/Llama3-8B-ScaleQuest.i1-Q3_K_S.gguf new file mode 100644 index 0000000..79904cb --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5647abe5e36fb050dcfe9b50d625b80e95360b41ea8c57efa4082c490c8b4a46 +size 3664828864 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_0.gguf b/Llama3-8B-ScaleQuest.i1-Q4_0.gguf new file mode 100644 index 0000000..149edbc --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88eed46ce44ad19cb27188c71420e8d9edaea5bba30f10ee9e795668893a2b8 +size 4676256192 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_0_4_4.gguf b/Llama3-8B-ScaleQuest.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..318f5ca --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7b002537d04fbaba76272df292fba2c182923dad11cfb59944849837c2ac36 +size 4661576128 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_0_4_8.gguf b/Llama3-8B-ScaleQuest.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..0523e42 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b063d9d5976fdc09a317de550adbec34fb30c85a142d7627e675d3cf0f7350c7 +size 4661576128 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_0_8_8.gguf b/Llama3-8B-ScaleQuest.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..23c01ab --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10af0380a84954dbe4fc8ff3c774a6676737049b951f239457f9d6cf097e8468 +size 4661576128 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_K_M.gguf b/Llama3-8B-ScaleQuest.i1-Q4_K_M.gguf new file mode 100644 index 0000000..176fd41 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41d55f21d8d32b9b2cd9bedc341ca8a64cd87caf5631e1ebd3d9a8ebe607162 +size 4921098688 diff --git a/Llama3-8B-ScaleQuest.i1-Q4_K_S.gguf b/Llama3-8B-ScaleQuest.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7d72493 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6544398a7a6d10e87e0a26513e393ee0eb42024fec472fe0b83f79000b9a012c +size 4693033408 diff --git a/Llama3-8B-ScaleQuest.i1-Q5_K_M.gguf b/Llama3-8B-ScaleQuest.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8832eaa --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74d17300bdb5c1171171b8b93d7a5f8e0e70dac1117decb867325d81664dadd +size 5733384640 diff --git a/Llama3-8B-ScaleQuest.i1-Q5_K_S.gguf b/Llama3-8B-ScaleQuest.i1-Q5_K_S.gguf new file mode 100644 index 0000000..57b933a --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0038237e2646acbf288d8129b830c744f7a7482381f3ad98ca9b4e3b3b656dd2 +size 5599691200 diff --git a/Llama3-8B-ScaleQuest.i1-Q6_K.gguf b/Llama3-8B-ScaleQuest.i1-Q6_K.gguf new file mode 100644 index 0000000..88bb0c6 --- /dev/null +++ b/Llama3-8B-ScaleQuest.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8eddcc7522aca5fe95f64cd7ba3b445d3abbc1bdcbc02b2878d7d09dd89f58 +size 6596438464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..964e765 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: dyyyyyyyy/Llama3-8B-ScaleQuest +datasets: +- dyyyyyyyy/ScaleQuest-Math +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/dyyyyyyyy/Llama3-8B-ScaleQuest + + +static quants are available at https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-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/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-ScaleQuest-i1-GGUF/resolve/main/Llama3-8B-ScaleQuest.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..e742938 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f187da57ea0a36c4f4eacd83afbf81b21de8bafe03e39ff28d744501e61445 +size 4988157