commit ba7384c76c90d0f3271fa9c62adf6ab93aab7baa Author: ModelHub XC Date: Sun May 10 08:33:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HAREM-3.2-1B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e156f6 --- /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 +HAREM-3.2-1B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAREM-3.2-1B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HAREM-3.2-1B.i1-IQ1_M.gguf b/HAREM-3.2-1B.i1-IQ1_M.gguf new file mode 100644 index 0000000..d36780e --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372e10fdb3f58247986eb5f0e9480dd422b6edb9e6821416e89665991dea0cec +size 413606528 diff --git a/HAREM-3.2-1B.i1-IQ1_S.gguf b/HAREM-3.2-1B.i1-IQ1_S.gguf new file mode 100644 index 0000000..3eeb662 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95158392799f2cefec138d35cad8b00771170b9e2e0bb4228549ae4a33db9107 +size 393552512 diff --git a/HAREM-3.2-1B.i1-IQ2_M.gguf b/HAREM-3.2-1B.i1-IQ2_M.gguf new file mode 100644 index 0000000..c5f309f --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48c5e6e809cc31f790a5f830aec70809efc48c8f4ccc3c6b8e3504656cd3fe6 +size 515449472 diff --git a/HAREM-3.2-1B.i1-IQ2_S.gguf b/HAREM-3.2-1B.i1-IQ2_S.gguf new file mode 100644 index 0000000..bcbba34 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b605fa0b4a9bd9702d16528c038fcc97e30a5c905c5cc2c8789b926fb03404 +size 488710784 diff --git a/HAREM-3.2-1B.i1-IQ2_XS.gguf b/HAREM-3.2-1B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9926006 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41014764d4710633f52ea6497f7c99a2eda4074d8d858229b381eb6b896ece8 +size 475865728 diff --git a/HAREM-3.2-1B.i1-IQ2_XXS.gguf b/HAREM-3.2-1B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1624f7a --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5a3a31d8d7dd9db7fc85629850dda7de38cd98d2cb44e714a91870ff5af4e6 +size 447029888 diff --git a/HAREM-3.2-1B.i1-IQ3_M.gguf b/HAREM-3.2-1B.i1-IQ3_M.gguf new file mode 100644 index 0000000..88be60a --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b1c82708e7aec40bdba745324329821ceb21d1f40d322f3d5f3d36d99d04b5 +size 657289856 diff --git a/HAREM-3.2-1B.i1-IQ3_S.gguf b/HAREM-3.2-1B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1558ce8 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a27c3c280266cd5b64344f0326ea903712d52a7f4a0ae890ab4c9e9708d0f59 +size 643920512 diff --git a/HAREM-3.2-1B.i1-IQ3_XS.gguf b/HAREM-3.2-1B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d31ad83 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79f782d9d79b431b7e024574a0b0b84754cf3e0ffb09362521d7f6c24e47333 +size 621113984 diff --git a/HAREM-3.2-1B.i1-IQ3_XXS.gguf b/HAREM-3.2-1B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a5ece68 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4040e4a401000cf7f82e8da7b7351bdc557ab9831cb73d621ae67d0ed45207e +size 562111104 diff --git a/HAREM-3.2-1B.i1-IQ4_NL.gguf b/HAREM-3.2-1B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fde54b2 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f8dcd93f6a94490b827d94a06cd9b66d67d6508ebc4ea27563073d21ec4902 +size 773026432 diff --git a/HAREM-3.2-1B.i1-IQ4_XS.gguf b/HAREM-3.2-1B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..21aa669 --- /dev/null +++ b/HAREM-3.2-1B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98de47c0eeb7b3c55d5a46fce8a72a85e0e7377b9bf0fe2114fa952324192d4a +size 743142016 diff --git a/HAREM-3.2-1B.i1-Q2_K.gguf b/HAREM-3.2-1B.i1-Q2_K.gguf new file mode 100644 index 0000000..a7dcbc2 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75afa582b8233194d68d5b19dc03fb6ab06843c4fa16e79819a72028a4a9bde +size 580874880 diff --git a/HAREM-3.2-1B.i1-Q2_K_S.gguf b/HAREM-3.2-1B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..217f420 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06ec0da933b782e919b666dc2f3668e047c125c241c76f90990fdbb7fd7d96f +size 554660480 diff --git a/HAREM-3.2-1B.i1-Q3_K_L.gguf b/HAREM-3.2-1B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..dcd99ac --- /dev/null +++ b/HAREM-3.2-1B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76919901f305ccc86c2fe6dd895871dd1ea5a10e7f22a6ea42ac9caeedaeeae0 +size 732525184 diff --git a/HAREM-3.2-1B.i1-Q3_K_M.gguf b/HAREM-3.2-1B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..83944e9 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce570256e93ec89aeaacef4e35449b34e57cc4a091a0c19dc86dca9d9ca7b784 +size 690844288 diff --git a/HAREM-3.2-1B.i1-Q3_K_S.gguf b/HAREM-3.2-1B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ea91a04 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17adb05212e77f3c4552fcd0766929938ca1029b2b4453e4aa8582d39d57f237 +size 641692288 diff --git a/HAREM-3.2-1B.i1-Q4_0.gguf b/HAREM-3.2-1B.i1-Q4_0.gguf new file mode 100644 index 0000000..d57fb66 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f072888879f8cf4488174315dc2a2b913c5e722314009974b5ea31194f067c8a +size 773026432 diff --git a/HAREM-3.2-1B.i1-Q4_1.gguf b/HAREM-3.2-1B.i1-Q4_1.gguf new file mode 100644 index 0000000..2144cbe --- /dev/null +++ b/HAREM-3.2-1B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48404ccb3353d68fb500cba4c959db8d865694e3e8e1aca6344d0c0554507ae8 +size 831746688 diff --git a/HAREM-3.2-1B.i1-Q4_K_M.gguf b/HAREM-3.2-1B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b6a6f7c --- /dev/null +++ b/HAREM-3.2-1B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748c0d6d7bfcf487e16a09e319021715ad4e9ea4bf683e9c2658e73fe0a870df +size 807694976 diff --git a/HAREM-3.2-1B.i1-Q4_K_S.gguf b/HAREM-3.2-1B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..631487f --- /dev/null +++ b/HAREM-3.2-1B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c780a09a90c6afd57a038cf6656ac99666e4b85b659773ae4728a5a2053d17 +size 775647872 diff --git a/HAREM-3.2-1B.i1-Q5_K_M.gguf b/HAREM-3.2-1B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..567cc55 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0560b7fd313f70ae143ceac45b5af5869d222441fd5c39b1ea784cb649966db8 +size 911504000 diff --git a/HAREM-3.2-1B.i1-Q5_K_S.gguf b/HAREM-3.2-1B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..066b063 --- /dev/null +++ b/HAREM-3.2-1B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8a2fdb0e64ebc127500803f4efb5feee5e1a4473179fe8af5600a911cbd1e0 +size 892564096 diff --git a/HAREM-3.2-1B.i1-Q6_K.gguf b/HAREM-3.2-1B.i1-Q6_K.gguf new file mode 100644 index 0000000..372e9cf --- /dev/null +++ b/HAREM-3.2-1B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b77c706c5f3ecefd4c038f0d59ddc68b63eba5b7a79c7d6f57114e4c4e180b +size 1021801088 diff --git a/HAREM-3.2-1B.imatrix.gguf b/HAREM-3.2-1B.imatrix.gguf new file mode 100644 index 0000000..532d82d --- /dev/null +++ b/HAREM-3.2-1B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba1d943dc8c567f51dea95fa9251a7c31a9d0dea8f4e8d547fd5f2e4a9bf136 +size 1328000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a4cb2c --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: NovaCorp/HAREM-3.2-1B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/NovaCorp/HAREM-3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HAREM-3.2-1B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/HAREM-3.2-1B-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/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/HAREM-3.2-1B-i1-GGUF/resolve/main/HAREM-3.2-1B.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | 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. + +