commit b6e0cfc714f058b95cb4f141cd428b7c1d59f8cd Author: ModelHub XC Date: Fri Sep 11 06:37:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8f32175 --- /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 +Mistral_Pro_8B_v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Mistral_Pro_8B_v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral_Pro_8B_v0.1.i1-IQ1_M.gguf b/Mistral_Pro_8B_v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..e85247b --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38cf913bc8de27007923dd4392388ed8723f41d576f276f435dcb6f99b39da7 +size 2159595232 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ1_S.gguf b/Mistral_Pro_8B_v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..4a4d071 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86928e8cf6704618479c644655488397ec544f6a5234606079414c6a6c6b285 +size 1981664992 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ2_M.gguf b/Mistral_Pro_8B_v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..c35c8bf --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5144cd614c3ebc2cf77a1ce61668eac553af58c05be285879b4eb9ad3f6d4f3d +size 3089100512 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ2_S.gguf b/Mistral_Pro_8B_v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..b5865d0 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5019425b9971f3bb5ce08e44c75b32e60e8697d6eb408baaba921ddfbc11bf32 +size 2851860192 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ2_XS.gguf b/Mistral_Pro_8B_v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..42fa219 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2132639c3ed00e1a046118658c4f0a31a185c82d49dc54eff33fce58889f166a +size 2714357472 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ2_XXS.gguf b/Mistral_Pro_8B_v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..993c88c --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29e5cc9ae188b97e13fccafd0b5e27566fb82029b37c05d077da75912bfb358 +size 2456145632 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ3_M.gguf b/Mistral_Pro_8B_v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..f61a6c5 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e33cfcd6c88b998740754943aca6cf5ccea3cf997ce50e8d64d1e432051207f1 +size 4064972512 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ3_S.gguf b/Mistral_Pro_8B_v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..a06b0a6 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977a4eeba3c5d6e72acbb0adc9e040a03e7168366de00294ac6981806dfc0088 +size 3936849632 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ3_XS.gguf b/Mistral_Pro_8B_v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ea4a938 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7c5c834ccfe0b98635b527fbc4fadf653e802e8ca388cd104019d0de94b5db +size 3732377312 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ3_XXS.gguf b/Mistral_Pro_8B_v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..88b856c --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4c66a4d521b78affb2a964a2c6eb1d6cd060b73fe2aa2eda1d065d533ca5b0 +size 3497389792 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ4_NL.gguf b/Mistral_Pro_8B_v0.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..d324e94 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05707c12afc90c3d6f2b728bb542d09433d864c5ba118f1c30b4d826ec946b90 +size 5111623392 diff --git a/Mistral_Pro_8B_v0.1.i1-IQ4_XS.gguf b/Mistral_Pro_8B_v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..88950f9 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c806557c5fce3ca5c8b47ab4842d3d5b0cfb9a3a9b7983e5fd8a8cd57121e3 +size 4840140512 diff --git a/Mistral_Pro_8B_v0.1.i1-Q2_K.gguf b/Mistral_Pro_8B_v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..c2cc6f2 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:971e8d3dc9945b1cf5b13be75b338bb049cb111272d597f5a0390ef5b1d4f209 +size 3361238752 diff --git a/Mistral_Pro_8B_v0.1.i1-Q2_K_S.gguf b/Mistral_Pro_8B_v0.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..38e8c03 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c264b34997bfbcf90da29a9f4ff988b3f244ddf3614ff07853627956d6bbf6d3 +size 3123343072 diff --git a/Mistral_Pro_8B_v0.1.i1-Q3_K_L.gguf b/Mistral_Pro_8B_v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..39fec5c --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd337a5eee94071c0f9cc1439f0d892270a7e84354a061651c2c69b0da1b30a +size 4736388832 diff --git a/Mistral_Pro_8B_v0.1.i1-Q3_K_M.gguf b/Mistral_Pro_8B_v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f0470b8 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d48207158108a611bf8d55c4de3918b7953eee6c996f248c9cdd9546cc72ed3 +size 4353658592 diff --git a/Mistral_Pro_8B_v0.1.i1-Q3_K_S.gguf b/Mistral_Pro_8B_v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..dda1d75 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bf924df1da34afb99645ebebf2042f124040a08961d768896af6ddb85f5f67 +size 3914567392 diff --git a/Mistral_Pro_8B_v0.1.i1-Q4_0.gguf b/Mistral_Pro_8B_v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..1028d1a --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc24e2687d1c414cd11388c6d83a7e6847fb96fef0fdbef2893905da4a4c01f +size 5109001952 diff --git a/Mistral_Pro_8B_v0.1.i1-Q4_1.gguf b/Mistral_Pro_8B_v0.1.i1-Q4_1.gguf new file mode 100644 index 0000000..001c6fd --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0739000550d00bcc1aaf08398643efd9fbe1618fd797b9fbb606e823d05eb5 +size 5644103392 diff --git a/Mistral_Pro_8B_v0.1.i1-Q4_K_M.gguf b/Mistral_Pro_8B_v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c6c0d7c --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e87de65511d63a78bb1c97c41c99f0e848c2556416ee7e2b9251053c0288a29 +size 5415055072 diff --git a/Mistral_Pro_8B_v0.1.i1-Q4_K_S.gguf b/Mistral_Pro_8B_v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7bdc143 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7971c06c01ec36e592f043f346b8b6b40824fbcae00b581e3bbd24ca954f494 +size 5129449184 diff --git a/Mistral_Pro_8B_v0.1.i1-Q5_K_M.gguf b/Mistral_Pro_8B_v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c90a833 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5544b7dd0f5843d9fe5538cd3fe0aff0d1699c3fba23781cd848f5107292c890 +size 6364671712 diff --git a/Mistral_Pro_8B_v0.1.i1-Q5_K_S.gguf b/Mistral_Pro_8B_v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..bdf5cec --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d23198ce496174fe08bde2c3a0674bb0e080c769179e1e48be237c03131cd50 +size 6197554912 diff --git a/Mistral_Pro_8B_v0.1.i1-Q6_K.gguf b/Mistral_Pro_8B_v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..dc4e062 --- /dev/null +++ b/Mistral_Pro_8B_v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7730d0322d08929959425e8e93a39c90d12ef72257378d6c25ebed30842d31d6 +size 7373639392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0271d70 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: TencentARC/Mistral_Pro_8B_v0.1 +datasets: +- HuggingFaceTB/cosmopedia +- EleutherAI/proof-pile-2 +- bigcode/the-stack-dedup +- math-ai/AutoMathText +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-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/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q2_K.gguf) | i1-Q2_K | 3.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 5.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q4_1.gguf) | i1-Q4_1 | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral_Pro_8B_v0.1-i1-GGUF/resolve/main/Mistral_Pro_8B_v0.1.i1-Q6_K.gguf) | i1-Q6_K | 7.5 | 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..400cf8d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffb21c6edcb90c8a35bb52dae273798e6b05cadd4c60aa6c6c68dcc96c4f66a +size 6235205