commit bfb317603a761de7eb075270669a6ef79421aa03 Author: ModelHub XC Date: Thu May 14 19:38:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0da1af --- /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-3.1-EstLLM-8B-0525.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-EstLLM-8B-0525.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ1_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ1_M.gguf new file mode 100644 index 0000000..c73aea7 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b8d2c0a07c7816870539c57e681ff8f624bbf0e41123190477deb46f9a95cd +size 2161972864 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ1_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ1_S.gguf new file mode 100644 index 0000000..df2ef0f --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be22ae0642c9f05d257293f5fdd2f8fd5d4a241768e2dfc2c78fc5583dff0d71 +size 2019628672 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ2_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_M.gguf new file mode 100644 index 0000000..4580f8b --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f5e00eb0634c84840ddd101be41f68455da2bcef3d4b4934a1435941b10221 +size 2948281984 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ2_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_S.gguf new file mode 100644 index 0000000..95e2bf9 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee6b0ad24fca8f2c089d0ab4c1be844b2759196f091bb5746e727512c937fb6 +size 2758489728 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XS.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d40fbbc --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548e49ac58de2a0b4b7aab8e80a4836445fa7550d2c4784104502a3e29b1ae5f +size 2605782656 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XXS.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..88fb115 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c1c485f3289974a4ed1b53ddf49a442c1e2400db5e6fa7f9da3245f24633dc +size 2399213184 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ3_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_M.gguf new file mode 100644 index 0000000..1541c9d --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5557c4f063c27665cfa3240038ed680f468a3a6960fbcb0d5edabb4f435f6f +size 3784824448 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ3_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_S.gguf new file mode 100644 index 0000000..8b4dfda --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618899240e6ae05525656147fb730b58590ae33d4c12ad4e9cf50066856b0ce1 +size 3682326144 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XS.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e6e4db1 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6aa4e9d0befb3e644cce6aa74aa1b8d586ba611b01a79a7ad552360bcd252d +size 3518748288 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XXS.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7ccb2d9 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8d52ddfdd4de8da18191c2f528518026db411b9174a17f7ca90984510db3ed +size 3274913408 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ4_NL.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ4_NL.gguf new file mode 100644 index 0000000..01a5f5e --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7693f9656db50a3bd271e03d22a9712b780023b167370c10643c6b7af0e7f37a +size 4677990016 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-IQ4_XS.gguf b/Llama-3.1-EstLLM-8B-0525.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e0f4f0a --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57883da3cb64868a025fc9c39fa6026e6266081731d464647c3c5e88ab0d2f80 +size 4447663744 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q2_K.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q2_K.gguf new file mode 100644 index 0000000..99c809c --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1607bfd4c54dc1620ff4d4f531ddd6629912730982a932378f8ed317d369a3a +size 3179132544 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q2_K_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q2_K_S.gguf new file mode 100644 index 0000000..42aa506 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99da3be89930d66aacb10fae92c4394186616f9e584dcc436904eed78263ed56 +size 2988816000 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_L.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b7ff1f8 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1db9df61f2dea93b897af8ff6bce6d04aefbbe769101b783e59a3557a24e77c +size 4321957504 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_M.gguf new file mode 100644 index 0000000..44ae364 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcbc36053e684939faa51773af6d2e00c267481a5e145a674af3b303e9b84d1 +size 4018919040 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_S.gguf new file mode 100644 index 0000000..354af5e --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54fd5222b7dcc22bd61a634d146c17579610ee9047035968d1ab6573e1026bd9 +size 3664500352 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q4_0.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q4_0.gguf new file mode 100644 index 0000000..4b088bb --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753a3458c9570e480e53320578020431fbe6e4517a32d626b2579e291da61cb9 +size 4675892864 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q4_1.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q4_1.gguf new file mode 100644 index 0000000..5fedad3 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2207875d7c6be3cea48c08af5847dfd4552923b5844424ac8769b46e527e27 +size 5130253952 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_M.gguf new file mode 100644 index 0000000..918b9b6 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed026036ae5f499e24506b25024f99fa9548ca5349882590eb89622f54fc2973 +size 4920735360 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_S.gguf new file mode 100644 index 0000000..788f229 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e323cf1404948f5365a4a6f45caf6780c870455cc2311055803259667a22c083 +size 4692670080 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_M.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c561ba1 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14daa277a4bb2a105fec94bc156d8c5eebcd193ce9bf851574f041ceb31b141a +size 5732988544 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_S.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a4cf75b --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f2944730eaefe709f3d962549e8ecadfeb0610a5613ea52eb5e8b99b3a3c3e +size 5599295104 diff --git a/Llama-3.1-EstLLM-8B-0525.i1-Q6_K.gguf b/Llama-3.1-EstLLM-8B-0525.i1-Q6_K.gguf new file mode 100644 index 0000000..1201e49 --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af9995386d886871e990e307da252054c42b5dac80628515e1926c57c327eda +size 6596007552 diff --git a/Llama-3.1-EstLLM-8B-0525.imatrix.gguf b/Llama-3.1-EstLLM-8B-0525.imatrix.gguf new file mode 100644 index 0000000..ca6228a --- /dev/null +++ b/Llama-3.1-EstLLM-8B-0525.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6066bf8f05bed1d8963d3a6905fb705f8f36a427ede3b145a5282a37aacfedf3 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a6b28ba --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: tartuNLP/Llama-3.1-EstLLM-8B-0525 +datasets: +- HuggingFaceTB/smollm-corpus +- HuggingFaceTB/finemath +- instruction-pretrain/general-instruction-augmented-corpora +language: +- en +- et +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/tartuNLP/Llama-3.1-EstLLM-8B-0525 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-EstLLM-8B-0525-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-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-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-EstLLM-8B-0525-i1-GGUF/resolve/main/Llama-3.1-EstLLM-8B-0525.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. + +