commit eac208de0ac6670792143687d297d68330512a01 Author: ModelHub XC Date: Wed May 13 08:52:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Impish_LLAMA_4B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..817ebb8 --- /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 +Impish_LLAMA_4B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_LLAMA_4B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Impish_LLAMA_4B.i1-IQ1_M.gguf b/Impish_LLAMA_4B.i1-IQ1_M.gguf new file mode 100644 index 0000000..ffc4b17 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6c38a4c39c1f001321a616408747e96f525358ed977f31cdea607e218e5e7b +size 1286256704 diff --git a/Impish_LLAMA_4B.i1-IQ1_S.gguf b/Impish_LLAMA_4B.i1-IQ1_S.gguf new file mode 100644 index 0000000..b9458ce --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98d23a4b6ae1834ba71f423a20cf18b3d6bb3725fd432644ddc6907842f66a5 +size 1213413440 diff --git a/Impish_LLAMA_4B.i1-IQ2_M.gguf b/Impish_LLAMA_4B.i1-IQ2_M.gguf new file mode 100644 index 0000000..f4aa1e3 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a596ff3b114d8e1cfcacf1c735241ed7df91842774ea6e25c4bdb3654a5baa5 +size 1722634304 diff --git a/Impish_LLAMA_4B.i1-IQ2_S.gguf b/Impish_LLAMA_4B.i1-IQ2_S.gguf new file mode 100644 index 0000000..bbbf088 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e3b5faaebcb76326f488386bbf6f14b7f90a9575c424e80a4e0c11bfd25a73 +size 1625509952 diff --git a/Impish_LLAMA_4B.i1-IQ2_XS.gguf b/Impish_LLAMA_4B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7aa6807 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7225fd28d4bc6f6de4c81f753df2ddb851998556adf79125115a50be3836e9e2 +size 1517369408 diff --git a/Impish_LLAMA_4B.i1-IQ2_XXS.gguf b/Impish_LLAMA_4B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bcaaced --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c7d3a27c6ee95f0a7b3c785264bc4cda3036c933bd4a6b4489c97d0e8c6227 +size 1407662144 diff --git a/Impish_LLAMA_4B.i1-IQ3_M.gguf b/Impish_LLAMA_4B.i1-IQ3_M.gguf new file mode 100644 index 0000000..b961080 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b68fa4ccdf1e3ad37c7d8e7b4136d059c8f3eed6f5b3987d08e87d5650d676d +size 2183415872 diff --git a/Impish_LLAMA_4B.i1-IQ3_S.gguf b/Impish_LLAMA_4B.i1-IQ3_S.gguf new file mode 100644 index 0000000..70b266a --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecc037a1d8396c95641172f4271d7d877bd31889d66a3fa4e714043fe02edc5 +size 2114897984 diff --git a/Impish_LLAMA_4B.i1-IQ3_XS.gguf b/Impish_LLAMA_4B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..78977e4 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d7b060af0d3b4e2c2649f1f8297968a9d262d8b9f8917f080e7f165e608739d +size 2027604032 diff --git a/Impish_LLAMA_4B.i1-IQ3_XXS.gguf b/Impish_LLAMA_4B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8f044aa --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35889d2d676e792c0d8fe5fbe2839d4f3d9d2193a6002b76310129f306717a17 +size 1880117312 diff --git a/Impish_LLAMA_4B.i1-IQ4_NL.gguf b/Impish_LLAMA_4B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5ffb318 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89496dd0676cea56a31576e6f09e6a3ce67ffe85a37ad599fe6c3c8f3709a04d +size 2661105728 diff --git a/Impish_LLAMA_4B.i1-IQ4_XS.gguf b/Impish_LLAMA_4B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..58b9090 --- /dev/null +++ b/Impish_LLAMA_4B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37cd35dbae674a472bea1b9d525ff0e1d5f58466099301b3ea5132f0f8c37e3a +size 2535546944 diff --git a/Impish_LLAMA_4B.i1-Q2_K.gguf b/Impish_LLAMA_4B.i1-Q2_K.gguf new file mode 100644 index 0000000..77c92d2 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714cbde05ccb77693ff5a68e5bdd09256f9bfe61aa96412f8ec301bbe4d5cecf +size 1839738944 diff --git a/Impish_LLAMA_4B.i1-Q2_K_S.gguf b/Impish_LLAMA_4B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9cceac9 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35140d1158b96e7cc5bf5240ae2dd61edeeae8499b302cbf79fee6af5130500 +size 1733374016 diff --git a/Impish_LLAMA_4B.i1-Q3_K_L.gguf b/Impish_LLAMA_4B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..902a5e8 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7145f275b12be48c2c2493eff6d659ecac302f5b0168577114402676b142431 +size 2464860224 diff --git a/Impish_LLAMA_4B.i1-Q3_K_M.gguf b/Impish_LLAMA_4B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..913caf1 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbc86b4a67b203982745296a40fcce82054b9dc91dea0aaa52d84e181ecd948 +size 2296563776 diff --git a/Impish_LLAMA_4B.i1-Q3_K_S.gguf b/Impish_LLAMA_4B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7437d6b --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d8615ffd6cc827b3e40da73510608b56da763111689330efb14a683f73de2d +size 2101528640 diff --git a/Impish_LLAMA_4B.i1-Q4_0.gguf b/Impish_LLAMA_4B.i1-Q4_0.gguf new file mode 100644 index 0000000..7a428f5 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e25edc0c7d015c41aa1ec37b7da8515a673a6eb8d3811e4d74b6ad2f30d1d3 +size 2655600704 diff --git a/Impish_LLAMA_4B.i1-Q4_1.gguf b/Impish_LLAMA_4B.i1-Q4_1.gguf new file mode 100644 index 0000000..3d86a9f --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65d4dec776e5c4891a7c99ca44d1b3bc40a550dfe19a76ca13095c1b7a3664f +size 2905931840 diff --git a/Impish_LLAMA_4B.i1-Q4_K_M.gguf b/Impish_LLAMA_4B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7b1c241 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890b211ef6caf0b2d0d338f3bc16bf3eff7cfb693b369b3b02faa2da263c950a +size 2778284096 diff --git a/Impish_LLAMA_4B.i1-Q4_K_S.gguf b/Impish_LLAMA_4B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c5d5d0f --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e5feba2514d0ccf8015df566eefe44da14be0efaa4d5bb828c0665b711531d +size 2664251456 diff --git a/Impish_LLAMA_4B.i1-Q5_K_M.gguf b/Impish_LLAMA_4B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cffc626 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a4c2add83a06e43049285e48d95dfeb97a0a54798cc48684664f7dbf0a415e +size 3230187584 diff --git a/Impish_LLAMA_4B.i1-Q5_K_S.gguf b/Impish_LLAMA_4B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b548207 --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb73800bc638a3530ba730be41811b9d99c95df30447ca8166d7f9e70543b124 +size 3163340864 diff --git a/Impish_LLAMA_4B.i1-Q6_K.gguf b/Impish_LLAMA_4B.i1-Q6_K.gguf new file mode 100644 index 0000000..e0e91ab --- /dev/null +++ b/Impish_LLAMA_4B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5370e469b1a64bb699a6c2bc991fd17569f9622a5e45aed22f2a6a3690400dd5 +size 3710335040 diff --git a/Impish_LLAMA_4B.imatrix.gguf b/Impish_LLAMA_4B.imatrix.gguf new file mode 100644 index 0000000..9fa44e3 --- /dev/null +++ b/Impish_LLAMA_4B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b194d2b900bed9998906af406095c6f8588091ab2180b31716ec1c69ebc93c7 +size 3704480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f49c8b3 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: SicariusSicariiStuff/Impish_LLAMA_4B +datasets: +- SicariusSicariiStuff/UBW_Tapestries +language: +- en +library_name: transformers +license: other +license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf +license_name: nvidia-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/SicariusSicariiStuff/Impish_LLAMA_4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Impish_LLAMA_4B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Impish_LLAMA_4B-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/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q4_1.gguf) | i1-Q4_1 | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_LLAMA_4B-i1-GGUF/resolve/main/Impish_LLAMA_4B.i1-Q6_K.gguf) | i1-Q6_K | 3.8 | 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. + +