commit 0e8f0f8a26ab3d295c1b4c35802532a8070bc22c Author: ModelHub XC Date: Wed Apr 22 11:50:37 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/PrimaSumika-10.7B-128k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..36de1e1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.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 +PrimaSumika-10.7B-128k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +PrimaSumika-10.7B-128k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PrimaSumika-10.7B-128k.i1-IQ1_M.gguf b/PrimaSumika-10.7B-128k.i1-IQ1_M.gguf new file mode 100644 index 0000000..6c01f89 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1d1c2245a157993196e3a6ec7908d28e97f98c71241e283b43504c7950d758 +size 2564742720 diff --git a/PrimaSumika-10.7B-128k.i1-IQ1_S.gguf b/PrimaSumika-10.7B-128k.i1-IQ1_S.gguf new file mode 100644 index 0000000..3f84d08 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b118e3ee3fc0579daa534f1d83efa46c36c36c0a2627543007897a539587c6ae +size 2351226432 diff --git a/PrimaSumika-10.7B-128k.i1-IQ2_M.gguf b/PrimaSumika-10.7B-128k.i1-IQ2_M.gguf new file mode 100644 index 0000000..ba02e8f --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abd0b5519cdb82554d9d46b223bc85bf1ed50d9849359d75773f735366fba51 +size 3677486656 diff --git a/PrimaSumika-10.7B-128k.i1-IQ2_S.gguf b/PrimaSumika-10.7B-128k.i1-IQ2_S.gguf new file mode 100644 index 0000000..3ca8353 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8708f4547b8bce71284864d0874e840d6795896f730404f3aa5a5a50492cb250 +size 3392798272 diff --git a/PrimaSumika-10.7B-128k.i1-IQ2_XS.gguf b/PrimaSumika-10.7B-128k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..516ce43 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916a6dc6d6f4366251826457b683d331b7266f1a38db949b765c3fa7fb4332ec +size 3230457408 diff --git a/PrimaSumika-10.7B-128k.i1-IQ2_XXS.gguf b/PrimaSumika-10.7B-128k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..eb016ca --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e7ed8867f57af8e7f66cdf8333decff22d74fc87b754f5d65655fc9c2ccb32 +size 2920603200 diff --git a/PrimaSumika-10.7B-128k.i1-IQ3_M.gguf b/PrimaSumika-10.7B-128k.i1-IQ3_M.gguf new file mode 100644 index 0000000..b0abcf3 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2736f2126906dcfeb19a3b6d78ba8a5a70d524f4ff5b52f26552f99f4e5e1c55 +size 4845051456 diff --git a/PrimaSumika-10.7B-128k.i1-IQ3_S.gguf b/PrimaSumika-10.7B-128k.i1-IQ3_S.gguf new file mode 100644 index 0000000..7bbea94 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ac641c81ab82176170a1573b789981150ca9da4e924212dced2408df6b001b +size 4691304000 diff --git a/PrimaSumika-10.7B-128k.i1-IQ3_XS.gguf b/PrimaSumika-10.7B-128k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0ac2f83 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad866263ea33bdbeeb016bdcded5e14110d1201623f2bd941ce5e968298018d +size 4445937216 diff --git a/PrimaSumika-10.7B-128k.i1-IQ3_XXS.gguf b/PrimaSumika-10.7B-128k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bf57ff4 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3891578db8e839b9a052d89ec7d5f82e0a37fcc6e90dcc0fcb7e56f7edcbfff8 +size 4167433792 diff --git a/PrimaSumika-10.7B-128k.i1-IQ4_XS.gguf b/PrimaSumika-10.7B-128k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..750d112 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc1a5e889dc3213b23a7cba22c6ed1e3d8763b716c9f0a97415905616f981b7 +size 5772590656 diff --git a/PrimaSumika-10.7B-128k.i1-Q2_K.gguf b/PrimaSumika-10.7B-128k.i1-Q2_K.gguf new file mode 100644 index 0000000..c375fbf --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afed75b5fa8dba729d932acfec41a58067511703e61d8142402cc652a6c9d75 +size 4003233344 diff --git a/PrimaSumika-10.7B-128k.i1-Q2_K_S.gguf b/PrimaSumika-10.7B-128k.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f6bec5e --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88feb354cab86495544836a28946a6a9e2693c3eb42ad0c4786949e25eeee918 +size 3717758528 diff --git a/PrimaSumika-10.7B-128k.i1-Q3_K_L.gguf b/PrimaSumika-10.7B-128k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d4429e2 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1c1bba9baf82d1c80d9055cafb441c75764f9054a176c255a1cae6fcb444e5 +size 5650751040 diff --git a/PrimaSumika-10.7B-128k.i1-Q3_K_M.gguf b/PrimaSumika-10.7B-128k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..73d4dc6 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451f96018e01cb24fef0a5fa88e5f490a99703f8cee9f796ba78d75da6ca7e19 +size 5195669056 diff --git a/PrimaSumika-10.7B-128k.i1-Q3_K_S.gguf b/PrimaSumika-10.7B-128k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b0f790e --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c42b7387697b86d2f18c6207f5b1d96ea22bd213df7515b44890649fa4b2af +size 4664565312 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_0.gguf b/PrimaSumika-10.7B-128k.i1-Q4_0.gguf new file mode 100644 index 0000000..fccd323 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a677a13441f8e8b8e94c793d41ba5c47cd13b0d4cb8331b3efe06fd68ee55896 +size 6094405184 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_0_4_4.gguf b/PrimaSumika-10.7B-128k.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..9359325 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1159765f4d3f2c9b073ac195ffa62fb1b75987ab99532ddf12edca6ecd51d8d +size 6072385088 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_0_4_8.gguf b/PrimaSumika-10.7B-128k.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..9717909 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf2c00bc0b52cfb4bc929ad0ad51a5a97310f0262b1bac9b140c481a95546b7 +size 6072385088 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_0_8_8.gguf b/PrimaSumika-10.7B-128k.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..3ec4f24 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534ad8ddf3b4a27fccf059bb00f4b89d2e32450e5c529249f8473c53ff5eb9a9 +size 6072385088 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_K_M.gguf b/PrimaSumika-10.7B-128k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9e2d498 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52be357f665e506ea61dd65ceea8326e245455d0346a087ba433808390ffa628 +size 6461668928 diff --git a/PrimaSumika-10.7B-128k.i1-Q4_K_S.gguf b/PrimaSumika-10.7B-128k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2dc0e20 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6c307ab7580ec324d5ad2dfe8e43c58ac48707318fc3fe956349cdf946c652 +size 6118522432 diff --git a/PrimaSumika-10.7B-128k.i1-Q5_K_M.gguf b/PrimaSumika-10.7B-128k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8e81b86 --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31284fda9b972e947f52ea0447a7d71bb41999d83576306d1010291599104301 +size 7597932096 diff --git a/PrimaSumika-10.7B-128k.i1-Q5_K_S.gguf b/PrimaSumika-10.7B-128k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..40c65bc --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb7861ad432c9923d37c8247f30a8adb14e558fc8361fcb4752cb174676af83 +size 7397391936 diff --git a/PrimaSumika-10.7B-128k.i1-Q6_K.gguf b/PrimaSumika-10.7B-128k.i1-Q6_K.gguf new file mode 100644 index 0000000..8514fae --- /dev/null +++ b/PrimaSumika-10.7B-128k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aac848004d2b22941634a98fd27d6bc10b7f3cb65515554afffa93a31a0e230 +size 8805211712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8173862 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: xxx777xxxASD/PrimaSumika-10.7B-128k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- moe +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/xxx777xxxASD/PrimaSumika-10.7B-128k + + +static quants are available at https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-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/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/PrimaSumika-10.7B-128k-i1-GGUF/resolve/main/PrimaSumika-10.7B-128k.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | 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..ab9ae2d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0de51d2cfd3d771e255ea1d6af69ad46237d346ccc17ef98efc9a60e001baa5 +size 7482253