commit 94832368be82e887b21a9b1f4bfe4fd7b63be862 Author: ModelHub XC Date: Mon Sep 28 06:20:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef6b5b8 --- /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 +Llama-3.2-3B-Instruct-heretic.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-heretic.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ1_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ1_M.gguf new file mode 100644 index 0000000..75d5edc --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb606cbe4925e306665f698d1398c55f36e66c59b598dc15d59b257df87cabe +size 924191680 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ1_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ1_S.gguf new file mode 100644 index 0000000..916c8cd --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00730e89e6b0d825b602f48253e8e688fc7202b27684a799a8c422ae05db20b4 +size 868158400 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ2_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_M.gguf new file mode 100644 index 0000000..bde4f49 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415619748c3979441957794527367cb3961eec62b3af94456a66bed76d5642e0 +size 1229032384 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ2_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_S.gguf new file mode 100644 index 0000000..b13b1aa --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fad187dff10dfe1486c058ee9bd612d6d9ea35c9ec5fd44bf8d988609fd6096 +size 1154321344 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XS.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XS.gguf new file mode 100644 index 0000000..892d3b6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53010f6bd3e5be0cd8f11e3d5c31809ea86bf4f737757781c9eb5f527c4893e +size 1100549056 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XXS.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5aeb352 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2bc6373647a538d6b802de06f0b2d2c1a1179780f21efaa1398a7d9f3bebc1 +size 1017580480 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ3_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_M.gguf new file mode 100644 index 0000000..abf9994 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0357a2aaa61c39b9be096848dc9be547e9580dc7f7e3d6d4010b10c47a369b74 +size 1599669184 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ3_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_S.gguf new file mode 100644 index 0000000..18250b8 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142eee177b41e7a431f5f3bd2b18a5a0230ac66d0163a5ce32d5de124ad47b2f +size 1542849472 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XS.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1e886dc --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c409021764c8b6fad2930249c4ab8d51f61689d2f402ec92562f7585183494 +size 1476789184 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XXS.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..80c97f7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01476b1bf8d948c6a693f8aa2f9ea5673a68eee3036e026236bb9dcd5df9935 +size 1348766656 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ4_NL.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ4_NL.gguf new file mode 100644 index 0000000..bb754e2 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae23c9d7ea1e3c4446a4fbc8314988d98d978c415abbd87f9132adf8239f9e5 +size 1917191104 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-IQ4_XS.gguf b/Llama-3.2-3B-Instruct-heretic.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0c9735a --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af52a5e0f41b7624be9d0a2fa89292cbe1dae94e08a53dee1c73ad2235bedbc5 +size 1829110720 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q2_K.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q2_K.gguf new file mode 100644 index 0000000..4a21d90 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4da512244044eccfa8ca024468a481bc750d3316105004063bea1dd5d6ed3cb +size 1363936192 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q2_K_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q2_K_S.gguf new file mode 100644 index 0000000..fde8722 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e70f6364d3fa920d635f932c8a4bad70ae60ff3c02cc46bf0541dbbe3ef4160 +size 1274282944 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_L.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cc4eec9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac69f4d48b3a25c6b1a451cdcd00f86ccb199a6b8f531badf452a24c81ac5ac +size 1815348160 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f142409 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda0ff13baf8283f318948e19306cbc31751c302afa3b51c77da230c2917c27f +size 1687159744 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1b4885c --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:318ac9393c0cd43743ab6d0030185e277163a44310692a8d4d13a65fdf2a2455 +size 1542849472 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q4_0.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q4_0.gguf new file mode 100644 index 0000000..a5bcd4d --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632031feb3f872fa80feb20da26d5b6bbf925845f086ef98c7604247b2ad56ec +size 1921909696 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q4_1.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q4_1.gguf new file mode 100644 index 0000000..02406f1 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f89c39ad7e129e0531d5a64d5aee176e8761c7142459318fc0d31e26c9c6a1 +size 2093351872 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2d72834 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3e5aaa4ae0c29890bf1790f44f3c6cfdda9cdc097569f8b225e39e8cf11159 +size 2019378112 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4c75790 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dbf4f2a193f0a6fd501e0eea4e0fccc90e11409aff953c8b363c7d39f629277 +size 1928201152 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_M.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_M.gguf new file mode 100644 index 0000000..174048f --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be733235f2754dd91b07a597a812f6763045459aa54695677ce27b035a7e2c3 +size 2322154432 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_S.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_S.gguf new file mode 100644 index 0000000..27ef4d2 --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8956546036dc4c5547ec04dd95855376140d5cb9560be6e149fb0ce392fdb129 +size 2269512640 diff --git a/Llama-3.2-3B-Instruct-heretic.i1-Q6_K.gguf b/Llama-3.2-3B-Instruct-heretic.i1-Q6_K.gguf new file mode 100644 index 0000000..3894fab --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cb6f8b2151c6fb70c39c65212a0346a03b7950c570648d461ea9357d8c3fe6 +size 2643854272 diff --git a/Llama-3.2-3B-Instruct-heretic.imatrix.gguf b/Llama-3.2-3B-Instruct-heretic.imatrix.gguf new file mode 100644 index 0000000..971797a --- /dev/null +++ b/Llama-3.2-3B-Instruct-heretic.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acaadf46680ae29531ff15604b0f85fe45b59c88b7b87fc158caba5a706ffe96 +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe6c0ac --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: rawcell/Llama-3.2-3B-Instruct-heretic +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/rawcell/Llama-3.2-3B-Instruct-heretic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-heretic-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-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/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-heretic-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-heretic.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + +