commit 01319069c0b168440307fa6f91f5f80800a87f9e Author: ModelHub XC Date: Wed Jun 17 17:29:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..604cfd6 --- /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-Nemo-Prism-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Prism-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-Nemo-Prism-12B.i1-IQ1_M.gguf b/Mistral-Nemo-Prism-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..8e00a2d --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f7c266a832ffd8e4d9fc4e4586cc8a302a5a0054a3a0bea0f6f175e36b43e9 +size 3221624832 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ1_S.gguf b/Mistral-Nemo-Prism-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..b4efdcd --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a88245735c7d939285c38793d58311d84fce161cabc5f058891c543abc9a2de +size 2999212032 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ2_M.gguf b/Mistral-Nemo-Prism-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..747a515 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe666505fb50a3d6f4dc11a3a1228d7f2556af3e0ba1ca74dc081ccfe63fcac +size 4435023872 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ2_S.gguf b/Mistral-Nemo-Prism-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..8f4d063 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362a6c7f07f0156ac3191f925fe62277dceae45300c45561d248240cdfb14410 +size 4138473472 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ2_XS.gguf b/Mistral-Nemo-Prism-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e26b391 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8965e7bebde96874eca01a12006e88980c72b0e63f8075b7ee1c6bba2149521e +size 3915077632 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ2_XXS.gguf b/Mistral-Nemo-Prism-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3ae2f8d --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141fd86f62601995e46a08aab9c4e54a73facf3b251d799c6a7fc42a11dc0a44 +size 3592312832 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ3_M.gguf b/Mistral-Nemo-Prism-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..00ee91a --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d064f07239738a0ab8801551580ae30aa482a1b4be87aa838c2f68c71fe007dd +size 5722232832 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ3_S.gguf b/Mistral-Nemo-Prism-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..b76c34d --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:768a75e139e5ea16dcdc8c70c0f8d0c8c1c38880053a1b3c96f88a7cbfce183b +size 5562079232 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ3_XS.gguf b/Mistral-Nemo-Prism-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..35e0f09 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5269d7344e0f6eb274b4299fc2a1dd9fafa5525b74a5f10686abecaa29cae57 +size 5306488832 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ3_XXS.gguf b/Mistral-Nemo-Prism-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5b4a792 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099b9888d6462ee5ee7c32636873bdaa1d47aaa4446aa50106d649fc17d758af +size 4945385472 diff --git a/Mistral-Nemo-Prism-12B.i1-IQ4_XS.gguf b/Mistral-Nemo-Prism-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e5b0aa7 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2744fac304caafd252398699b458a29855fa8571a7d09108b4ebc02fe0fdd0d3 +size 6742710272 diff --git a/Mistral-Nemo-Prism-12B.i1-Q2_K.gguf b/Mistral-Nemo-Prism-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..b2815ee --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86d1ffd1c906aed541085bd68e22e6bb8cf6e9316c011ac2be51182bfce5c5b +size 4791048192 diff --git a/Mistral-Nemo-Prism-12B.i1-Q3_K_L.gguf b/Mistral-Nemo-Prism-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cf17fdb --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd8e0362c8bb52fbf70317bdc1bbd7c7a603d5158ae8c2188d861e49e26f008 +size 6561503232 diff --git a/Mistral-Nemo-Prism-12B.i1-Q3_K_M.gguf b/Mistral-Nemo-Prism-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7da04d6 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfca93d994808c01f347381ca71cbe611894cf61def6464e1f2f9f5a6c1ba7a +size 6083090432 diff --git a/Mistral-Nemo-Prism-12B.i1-Q3_K_S.gguf b/Mistral-Nemo-Prism-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0d7aa01 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11cccd39ce2677fd8201b2c157d146a03ac8884a65f312890b101e22cb9e192d +size 5534226432 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_0.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..0723346 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d047887332af0ab54a0f317866e037ce3d13abea74b5eb0f27a585d45002f260 +size 7094638592 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_0_4_4.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..d52f854 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab34e32963d667fac0bacbe1e3a2b71ef4d5ee66668a335da98380f9225fc2b +size 7071700992 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_0_4_8.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..9b5e327 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bba9adb8ef71f711c980e52557051c5736534b30ed8c8ba896939f5b0be1028 +size 7071700992 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_0_8_8.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..2637d57 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85b3b0534021d848cc379bdd230468104cf8f620b099927312b639d423f4f06 +size 7071700992 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_K_M.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..884e6b8 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8b897808e4d4c81aa45d5075188140e06471b341a4a4564726766454e45c89 +size 7477204992 diff --git a/Mistral-Nemo-Prism-12B.i1-Q4_K_S.gguf b/Mistral-Nemo-Prism-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3a35848 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4361acbb7e9c948474c99f0ea02eda90ad63f4e63c4b8029372aba885decc442 +size 7120197632 diff --git a/Mistral-Nemo-Prism-12B.i1-Q5_K_M.gguf b/Mistral-Nemo-Prism-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..53c3423 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e17a3a95ba6651e3607141f1454526ebf05d3824b2d366fdb443e269b3431b +size 8727631872 diff --git a/Mistral-Nemo-Prism-12B.i1-Q5_K_S.gguf b/Mistral-Nemo-Prism-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..01eaca4 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8201ac869ee041fdcd2a7d94c3629063614f919a85eda64cd6ad8333f9732ce4 +size 8518735872 diff --git a/Mistral-Nemo-Prism-12B.i1-Q6_K.gguf b/Mistral-Nemo-Prism-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..2873318 --- /dev/null +++ b/Mistral-Nemo-Prism-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40cc4ff967fb43a14c265c5320a181c2721784b891ad143ae58e707cdc100ea4 +size 10056210432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e5baf1 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: nbeerbower/Mistral-Nemo-Prism-12B +datasets: +- nbeerbower/Arkhaios-DPO +- nbeerbower/Purpura-DPO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B + + +static quants are available at https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-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-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Prism-12B-i1-GGUF/resolve/main/Mistral-Nemo-Prism-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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..f93c827 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5bf18508c8d13447f4af99eff5c51d9117c8abaf35d71e69924cb3b6984d61 +size 7054405