commit d19788aa9b8736bbedcc483376eb93a999a7f8d3 Author: ModelHub XC Date: Thu May 28 13:00:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-EZO-8B-beta-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9ba72ba --- /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 +Qwen3-EZO-8B-beta.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-EZO-8B-beta.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-EZO-8B-beta.i1-IQ1_M.gguf b/Qwen3-EZO-8B-beta.i1-IQ1_M.gguf new file mode 100644 index 0000000..503fb33 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ff21da4935cdf1f57c91e5b0fb5a20fa084f93a0bb52692d9cd2f9bb6e3b1b +size 2256148384 diff --git a/Qwen3-EZO-8B-beta.i1-IQ1_S.gguf b/Qwen3-EZO-8B-beta.i1-IQ1_S.gguf new file mode 100644 index 0000000..99fa1b0 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f17071655e55323f9c69ab9b69033497f97c6f3a106c0499f586f5780c7b49 +size 2115770272 diff --git a/Qwen3-EZO-8B-beta.i1-IQ2_M.gguf b/Qwen3-EZO-8B-beta.i1-IQ2_M.gguf new file mode 100644 index 0000000..6168b95 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72fec085abb294644de272a9ae437af53b4bdadd6e596d18196742d18cbee4e7 +size 3051915168 diff --git a/Qwen3-EZO-8B-beta.i1-IQ2_S.gguf b/Qwen3-EZO-8B-beta.i1-IQ2_S.gguf new file mode 100644 index 0000000..5a1c6c5 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d8daca355dba272679dabae0b4f720d1c02e5e5690c67a4196e16c216ca36b +size 2864744352 diff --git a/Qwen3-EZO-8B-beta.i1-IQ2_XS.gguf b/Qwen3-EZO-8B-beta.i1-IQ2_XS.gguf new file mode 100644 index 0000000..813d7bd --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2afdf372670020bb267e83957c6012a7cdcbcd81bffe5f755a1ed206eae0fb +size 2696157088 diff --git a/Qwen3-EZO-8B-beta.i1-IQ2_XXS.gguf b/Qwen3-EZO-8B-beta.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9d5f624 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6935ab19b263f1bba451fbf5ef7a1a4f5d36329382c989da4c1ce14ef64fd964 +size 2490111904 diff --git a/Qwen3-EZO-8B-beta.i1-IQ3_M.gguf b/Qwen3-EZO-8B-beta.i1-IQ3_M.gguf new file mode 100644 index 0000000..a831293 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149f7561321a56ec85087cf2ed00835f75d2be2d349d75289bf26e3abcdf3005 +size 3896620960 diff --git a/Qwen3-EZO-8B-beta.i1-IQ3_S.gguf b/Qwen3-EZO-8B-beta.i1-IQ3_S.gguf new file mode 100644 index 0000000..c495b45 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886647f9dba856abfc325596001f335305d79900a04c5269c84b8d565b7ef3c7 +size 3789666208 diff --git a/Qwen3-EZO-8B-beta.i1-IQ3_XS.gguf b/Qwen3-EZO-8B-beta.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4c81c96 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4462d938a978f9b55a287097387920dd0ccc638b8a57ff2517e605c1ec8ad13 +size 3626874784 diff --git a/Qwen3-EZO-8B-beta.i1-IQ3_XXS.gguf b/Qwen3-EZO-8B-beta.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8c7ed2d --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448e956fe3f8c6197d6af61a26b16d5b7c2fb95e1821a21b633fdde37aa41f07 +size 3369633696 diff --git a/Qwen3-EZO-8B-beta.i1-IQ4_NL.gguf b/Qwen3-EZO-8B-beta.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cb1d1cd --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39fb6f84ff39a216190a4b338eab5f08fb7a9295084c5ba40beb8e42488dba8f +size 4793624480 diff --git a/Qwen3-EZO-8B-beta.i1-IQ4_XS.gguf b/Qwen3-EZO-8B-beta.i1-IQ4_XS.gguf new file mode 100644 index 0000000..409b10f --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccd320229124bb3e3b63b696aadd70213b89cbf0d501e6db5d5626e939ec4f0 +size 4561840032 diff --git a/Qwen3-EZO-8B-beta.i1-Q2_K.gguf b/Qwen3-EZO-8B-beta.i1-Q2_K.gguf new file mode 100644 index 0000000..46c3c90 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490db3167745cc9ec52a1230845e9515e2894a83f0c58c634cd30b4032b2b4a6 +size 3281733536 diff --git a/Qwen3-EZO-8B-beta.i1-Q2_K_S.gguf b/Qwen3-EZO-8B-beta.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0ee074e --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c081ae7797cda0e68c55115f5b80ddd4c3fe366de9d8943162d252556bfe2eb +size 3083552672 diff --git a/Qwen3-EZO-8B-beta.i1-Q3_K_L.gguf b/Qwen3-EZO-8B-beta.i1-Q3_K_L.gguf new file mode 100644 index 0000000..51832bb --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1ab1f6667ca956ff4f3fe3813a4aa04ab6236fa34ba9cedcd3daec89a9ff1ac +size 4431394720 diff --git a/Qwen3-EZO-8B-beta.i1-Q3_K_M.gguf b/Qwen3-EZO-8B-beta.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a20e425 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32be9d5d701350e95bdc7ae4063b9957c60e0062607b2a2537ec3477e4f2cb3b +size 4124161952 diff --git a/Qwen3-EZO-8B-beta.i1-Q3_K_S.gguf b/Qwen3-EZO-8B-beta.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1de016e --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16882f76379d5e4765071dc459418d8797bce207eef773471bac821e1682c846 +size 3769612192 diff --git a/Qwen3-EZO-8B-beta.i1-Q4_0.gguf b/Qwen3-EZO-8B-beta.i1-Q4_0.gguf new file mode 100644 index 0000000..979ec08 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d5ea9446866a210ff29982950b07e55cf56d592b10fbad9bac472580db44c6 +size 4787333024 diff --git a/Qwen3-EZO-8B-beta.i1-Q4_1.gguf b/Qwen3-EZO-8B-beta.i1-Q4_1.gguf new file mode 100644 index 0000000..7b17ff0 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65745dd2e45fedfd1b7e1d8ec8aaa392275c7962bd0b625e9d0fd8fafa43002 +size 5247756192 diff --git a/Qwen3-EZO-8B-beta.i1-Q4_K_M.gguf b/Qwen3-EZO-8B-beta.i1-Q4_K_M.gguf new file mode 100644 index 0000000..61839f9 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1055e1ae097eeab26cb64186cbecb4db8529120a2b253158def6cc62df2a0e54 +size 5027784608 diff --git a/Qwen3-EZO-8B-beta.i1-Q4_K_S.gguf b/Qwen3-EZO-8B-beta.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0d69482 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8427f08e29630bfdd0abf50b398269b2a6aa5595a2077cb9f48874546f3beb0 +size 4802013088 diff --git a/Qwen3-EZO-8B-beta.i1-Q5_K_M.gguf b/Qwen3-EZO-8B-beta.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ae7d7f5 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d92ed3ec36d597e2bd070933d65a26957032161d87d95f30b6130cde88038e0b +size 5851113376 diff --git a/Qwen3-EZO-8B-beta.i1-Q5_K_S.gguf b/Qwen3-EZO-8B-beta.i1-Q5_K_S.gguf new file mode 100644 index 0000000..92324ad --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95ad5f64a04690e325f413f25f3c87964f2ea501d61de294cb214ae83501240 +size 5720762272 diff --git a/Qwen3-EZO-8B-beta.i1-Q6_K.gguf b/Qwen3-EZO-8B-beta.i1-Q6_K.gguf new file mode 100644 index 0000000..1f067a6 --- /dev/null +++ b/Qwen3-EZO-8B-beta.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dcdc6a5128dd7f340abc478c0a4ca2d29c2c58eb77cdf0d3360191adac8287 +size 6725900192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..656b317 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: AXCXEPT/Qwen3-EZO-8B-beta +language: +- ja +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/AXCXEPT/Qwen3-EZO-8B-beta + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-EZO-8B-beta-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-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/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-EZO-8B-beta-i1-GGUF/resolve/main/Qwen3-EZO-8B-beta.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ea79dcf --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6592666861ad06aa61373c47ade76a5961ea891f6318020ba0ebc0a1643857b8 +size 5316769