commit ccf84e051321c65831953cbe9015a1746b942232 Author: ModelHub XC Date: Wed May 13 21:51:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..38a58d2 --- /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 +Heretic-Llama-3.2-3B-F1-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-3.2-3B-F1-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..d958970 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5cc1f617c3176b6e684e984c20e82195b6df196c1deab4d18c64c412f46a25 +size 924192224 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..3f3bdac --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec1a380a06159c211383225f65cff3c51548602103f472d5d3a307b049d2299 +size 868158944 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..8ef1c6c --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60601a58560f724cd0895d11f74bea5a59221d7c42b12143684a470dd5cdc9d +size 1229032928 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..3ec99a3 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa5f7b636b7a76c97e403c3f82db2ffcbee471c72c056b8cb52016aa5bc062c +size 1154321888 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ec548ff --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c2a6c152d03ca65453e481161e87a728a8a0647a99c062d19901df61679ced +size 1100549600 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XXS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..cb2a2fc --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ee9a4b1ec4671e2e6838b0b74e7bd56129f25e256c77e6d3bada00ad48ff9d +size 1017581024 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..fb65807 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64478213e9ed98cc2a8620cfaa3af7e4ad35bc9ee533a01570b12ebd73bb3ea +size 1599669728 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..9584403 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8477f0b0d428533f430838c81f10b64085320e7743de4e18881f5ed00cb7802 +size 1542850016 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..806d06b --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7ef09a8d8a235bb36798e5905451d69796de3ef8f1d7288ad5130a71ef92b0 +size 1476789728 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XXS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2804b47 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4c247459b9c477774f08b9577030ae7137cc1541dae986be3e591f4bb10191 +size 1348767200 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_NL.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..dca92af --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d7b941297add15c8e54d2b2ca0fb300039fd26941343c75fae44df98005b7b +size 1917191648 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_XS.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0f2d4ad --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784748a392b7aae9a8299d00ab9b570090aef1c7645984a9f03536b898f9548d +size 1829111264 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..491d7a6 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7124a5ff5b881a07a81ef9f664ff6f6c4a23ed967ca74737d133ccb6b8749e51 +size 1363936736 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7473775 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c854d5507ecc505c4d0804b1a20e12d3974ae91edc895cd924786750452dca1 +size 1274283488 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_L.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1ed0606 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9688b0d6dde58aafc317a58319f41495c3c747ae6043f027c1423a2257be8f +size 1815348704 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b13d307 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50d5e337764ac22d3a199e3ac6e202a709b5408bf5140e531801bee6271cdea +size 1687160288 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e4d05b0 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c859e9280de13e1b1fb2d3fcb00244e78f22ad0e8ffe9d6fa23a24d8f76d50b5 +size 1542850016 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_0.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..ef5ff72 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de4104069bfcd717e0173cac06f41cde91791daf3edf92a9c2802852d94b87a +size 1921910240 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_1.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..78291cc --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ce72eec01bdedce10dc7bed4affc7e7d7e134264cf2e8bad103f084a5c9bbb +size 2093352416 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5de6bd7 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343b3a4f0301a7b8567a2e3077d2ba7fa5de30990f9ee468c9e085a0f082f4e3 +size 2019378656 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7418bdb --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bf2f813248c0dfe8bca58eb6d55b96a9978d84d0a58c64a5027b50129997f0 +size 1928201696 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_M.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9555aae --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af76534ea6c87fbff0d845d0f404f7b72127b008a1798a3b6551bb1e28165181 +size 2322154976 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_S.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c1f952c --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdb7e66b9bc04697aeadfd1a3fb042677b3358d7bb23e37237b8f40df6732c3 +size 2269513184 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q6_K.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..1bb5c45 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86ab0f657b4b5b31288fd97e01ca125b9f5e10bea477a34dabb3ef6b119151d +size 2643854816 diff --git a/Heretic-Llama-3.2-3B-F1-Instruct.imatrix.gguf b/Heretic-Llama-3.2-3B-F1-Instruct.imatrix.gguf new file mode 100644 index 0000000..4ab59f8 --- /dev/null +++ b/Heretic-Llama-3.2-3B-F1-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3846a5f56969ecb9b614a1c45bc115f717a49c3487ec4f0090fad444c0b73a05 +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6d2136 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: hereticness/Heretic-Llama-3.2-3B-F1-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hereticness/Heretic-Llama-3.2-3B-F1-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-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/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-3.2-3B-F1-Instruct-i1-GGUF/resolve/main/Heretic-Llama-3.2-3B-F1-Instruct.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. + +