commit 6b88e8ab4ecba948a119ea95f92634ae40352573 Author: ModelHub XC Date: Mon May 11 02:22:33 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Artificium-llama3.1-8B-001-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0508f8 --- /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 +Artificium-llama3.1-8B-001.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Artificium-llama3.1-8B-001.i1-IQ1_M.gguf b/Artificium-llama3.1-8B-001.i1-IQ1_M.gguf new file mode 100644 index 0000000..635be65 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1834539878fc669d26e65b2f27c56e60758a8658fe9a5f22ea504d5c1718fb9 +size 2161976992 diff --git a/Artificium-llama3.1-8B-001.i1-IQ1_S.gguf b/Artificium-llama3.1-8B-001.i1-IQ1_S.gguf new file mode 100644 index 0000000..5260f98 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1177b377c5d79d15cdf4bd784e9063278f65b6f2490caf06cc8c142377ad7b40 +size 2019632800 diff --git a/Artificium-llama3.1-8B-001.i1-IQ2_M.gguf b/Artificium-llama3.1-8B-001.i1-IQ2_M.gguf new file mode 100644 index 0000000..5522b76 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90a2360d9afc305c5bfaa5a2cc148f1cbc02fb1e8b8fa327bbd2aa11a16df75 +size 2948286112 diff --git a/Artificium-llama3.1-8B-001.i1-IQ2_S.gguf b/Artificium-llama3.1-8B-001.i1-IQ2_S.gguf new file mode 100644 index 0000000..3ec5633 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d739963eb1a80ac37b8da90836a91ce521b0fe16497c63e41a00c80b9c8b62 +size 2758493856 diff --git a/Artificium-llama3.1-8B-001.i1-IQ2_XS.gguf b/Artificium-llama3.1-8B-001.i1-IQ2_XS.gguf new file mode 100644 index 0000000..52a915b --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cac774843afb8461451b5e5e953b14c21d71244ff58a79acbbe47adbbd99e34 +size 2605786784 diff --git a/Artificium-llama3.1-8B-001.i1-IQ2_XXS.gguf b/Artificium-llama3.1-8B-001.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..25a788e --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d66a1c179baeb1c5bb46e4f08d3ee7d2380171c1dae50de4f67678cbc4bf12 +size 2399217312 diff --git a/Artificium-llama3.1-8B-001.i1-IQ3_M.gguf b/Artificium-llama3.1-8B-001.i1-IQ3_M.gguf new file mode 100644 index 0000000..84e66bf --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91acc20e7300cd573f551a49fcb838fcdbb8d0365c09a38056f06114d4170f4b +size 3784828576 diff --git a/Artificium-llama3.1-8B-001.i1-IQ3_S.gguf b/Artificium-llama3.1-8B-001.i1-IQ3_S.gguf new file mode 100644 index 0000000..32dd2cc --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc9ccea9e3919376196c167661c48eb59b31140762d012980bed2b8c7207ce5b +size 3682330272 diff --git a/Artificium-llama3.1-8B-001.i1-IQ3_XS.gguf b/Artificium-llama3.1-8B-001.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ffef35b --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:febecc2602f53f404bcb17e36ea689b7a4c051fb0502a51049fc179ee781c7ca +size 3518752416 diff --git a/Artificium-llama3.1-8B-001.i1-IQ3_XXS.gguf b/Artificium-llama3.1-8B-001.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7e7f9ae --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3880fe66b3ac6513cfaab2762394f78453b1c112fa3ae20471863a67f75b9cca +size 3274917536 diff --git a/Artificium-llama3.1-8B-001.i1-IQ4_XS.gguf b/Artificium-llama3.1-8B-001.i1-IQ4_XS.gguf new file mode 100644 index 0000000..641fe27 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef108748b6253c80ddd2a3eebc325f9d23cdaddfcb929a92d7e7ad3efdefcc23 +size 4447667872 diff --git a/Artificium-llama3.1-8B-001.i1-Q2_K.gguf b/Artificium-llama3.1-8B-001.i1-Q2_K.gguf new file mode 100644 index 0000000..55cfd30 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f101bf1edff800b520760ebcce25ed849b45b164dd2adcbd2f1e0af5cc81190 +size 3179136672 diff --git a/Artificium-llama3.1-8B-001.i1-Q3_K_L.gguf b/Artificium-llama3.1-8B-001.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4f85cc6 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f19aa08d3d0fab88d6ca11dde608d4a024a2a7e64f1a6a86176bd09928ef97 +size 4321961632 diff --git a/Artificium-llama3.1-8B-001.i1-Q3_K_M.gguf b/Artificium-llama3.1-8B-001.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0c6a4e6 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950d48c55aa1ee08755eadfe010103bba8aec6182d032514041a178e1185bad9 +size 4018923168 diff --git a/Artificium-llama3.1-8B-001.i1-Q3_K_S.gguf b/Artificium-llama3.1-8B-001.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2a4507e --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4e2b7d91da5fbb51b4233ea7134e0040eb599da811cac2d151fcf2ac008d56 +size 3664504480 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_0.gguf b/Artificium-llama3.1-8B-001.i1-Q4_0.gguf new file mode 100644 index 0000000..e38af82 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:075de3b8aeffe21141c45c9a892d4a6d6614ef95dafc17d8e8ef828d14060606 +size 4675896992 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_0_4_4.gguf b/Artificium-llama3.1-8B-001.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..9104031 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9faa08593115d3b80e8b657a009e7276c5b9c48ef70006ad1e0709020019201c +size 4661216928 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_0_4_8.gguf b/Artificium-llama3.1-8B-001.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..0fa266f --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3519b90716bf9c59f8b42e6785fa2fc0385f70b6172cfc3d9c12ba30471e976 +size 4661216928 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_0_8_8.gguf b/Artificium-llama3.1-8B-001.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..acc1de3 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3299794c1dfff8f90b5855dac0a30e40955158615756e33f5cd472723ad572cb +size 4661216928 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_K_M.gguf b/Artificium-llama3.1-8B-001.i1-Q4_K_M.gguf new file mode 100644 index 0000000..55ef1f1 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27133c5dcfe447944b35caaf1c87aa309ef29d1fd6aafc64463ae67e1d0837a7 +size 4920739488 diff --git a/Artificium-llama3.1-8B-001.i1-Q4_K_S.gguf b/Artificium-llama3.1-8B-001.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ef64b11 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c551ecf6314d5b8b42a4a31e878049d8e9c7cce1424a1e0c0bf4d37ec4ca9a +size 4692674208 diff --git a/Artificium-llama3.1-8B-001.i1-Q5_K_M.gguf b/Artificium-llama3.1-8B-001.i1-Q5_K_M.gguf new file mode 100644 index 0000000..511d7d3 --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5676c4bebbec3f292731931afa4fea79892765e98d4d27bc66b18a5accb33591 +size 5732992672 diff --git a/Artificium-llama3.1-8B-001.i1-Q5_K_S.gguf b/Artificium-llama3.1-8B-001.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b2f38fe --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5211270b9f33da46fcb009837474307dcd0beb89267db0f1b5db3688d4a4121 +size 5599299232 diff --git a/Artificium-llama3.1-8B-001.i1-Q6_K.gguf b/Artificium-llama3.1-8B-001.i1-Q6_K.gguf new file mode 100644 index 0000000..989d0cf --- /dev/null +++ b/Artificium-llama3.1-8B-001.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:089ff8b1cf32b5c08753665d62d160f3943d90f8c794b383f2c0bb586413ef6c +size 6596011680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5bcc738 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AGI-0/smartllama3.1-8B-001 +language: +- en +library_name: transformers +license: unknown +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/AGI-0/smartllama3.1-8B-001 + + +static quants are available at https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-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/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-i1-GGUF/resolve/main/Artificium-llama3.1-8B-001.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..45d1c88 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745393aebd400f7decb105bb49eceaa61362d290cea6bc0b10824a7f50033a53 +size 4988157