commit 08e8363b3ce2341ca9fef6bc4d85024f175b99a5 Author: ModelHub XC Date: Tue Apr 14 02:47:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-0.5B-200K-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..487eed8 --- /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 +Qwen2.5-0.5B-200K.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-200K.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5B-200K.i1-IQ1_M.gguf b/Qwen2.5-0.5B-200K.i1-IQ1_M.gguf new file mode 100644 index 0000000..d8707c3 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de138e8630e7903a22e902f1cb68926f66ad39115b14ae97b9a6b6cbaf5c1e80 +size 317975296 diff --git a/Qwen2.5-0.5B-200K.i1-IQ1_S.gguf b/Qwen2.5-0.5B-200K.i1-IQ1_S.gguf new file mode 100644 index 0000000..fc818af --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9c9b9e9e4a86cd46d323cb8d9edd4b8c4f585d3bca03bb146169973cecb563 +size 315830272 diff --git a/Qwen2.5-0.5B-200K.i1-IQ2_M.gguf b/Qwen2.5-0.5B-200K.i1-IQ2_M.gguf new file mode 100644 index 0000000..90b49c2 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:482c8278a2012134241dd23133d13582acfbc9e9777bb523a13e6b34522dc53e +size 328598272 diff --git a/Qwen2.5-0.5B-200K.i1-IQ2_S.gguf b/Qwen2.5-0.5B-200K.i1-IQ2_S.gguf new file mode 100644 index 0000000..977d4e5 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bedd984aaf0eab6608ad7f01a32535339de7f9fdb5a46edc59c8c43c104747e +size 325738240 diff --git a/Qwen2.5-0.5B-200K.i1-IQ2_XS.gguf b/Qwen2.5-0.5B-200K.i1-IQ2_XS.gguf new file mode 100644 index 0000000..420e07d --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8979c7359708fb6d94b02ba9db1fecd621fed3c7d9a4f33cd503ba53214cc3d4 +size 324410368 diff --git a/Qwen2.5-0.5B-200K.i1-IQ2_XXS.gguf b/Qwen2.5-0.5B-200K.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..07d8768 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9138ea3d738091baff53fc8036a4e6704ba160efacbd6ee04876cc6ef6ce137b +size 321550336 diff --git a/Qwen2.5-0.5B-200K.i1-IQ3_M.gguf b/Qwen2.5-0.5B-200K.i1-IQ3_M.gguf new file mode 100644 index 0000000..6a1f2ac --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d802610d32680f039974aa27b4bae02234d3f7565f5018e0d926ee88108db12a +size 342753280 diff --git a/Qwen2.5-0.5B-200K.i1-IQ3_S.gguf b/Qwen2.5-0.5B-200K.i1-IQ3_S.gguf new file mode 100644 index 0000000..2b073f7 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f627220e22f82756e327f3b88cbff978e18cd8bf2f4fe45f91374a6642fe1d +size 338608384 diff --git a/Qwen2.5-0.5B-200K.i1-IQ3_XS.gguf b/Qwen2.5-0.5B-200K.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a5a457e --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8987d5bf9ad3a06831a79944b7be0d6b7c2ce819f49004aba20587a99e10f3 +size 338608384 diff --git a/Qwen2.5-0.5B-200K.i1-IQ3_XXS.gguf b/Qwen2.5-0.5B-200K.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a50d315 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bebc53bc6e84f7be1fcaa11f7dc1cf887445bc84c1ff93d4348e7d734a0f1ab +size 333705472 diff --git a/Qwen2.5-0.5B-200K.i1-IQ4_NL.gguf b/Qwen2.5-0.5B-200K.i1-IQ4_NL.gguf new file mode 100644 index 0000000..61b8267 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a900993a67b231df606774da864f8b9630879744c898ab4528f959035b15fbb +size 352672000 diff --git a/Qwen2.5-0.5B-200K.i1-IQ4_XS.gguf b/Qwen2.5-0.5B-200K.i1-IQ4_XS.gguf new file mode 100644 index 0000000..a509771 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bcbba077af9e77611286ed9c41b6950927d21e2ac5b9cd68d38c455db0c7475 +size 349403392 diff --git a/Qwen2.5-0.5B-200K.i1-Q2_K.gguf b/Qwen2.5-0.5B-200K.i1-Q2_K.gguf new file mode 100644 index 0000000..5aff8ab --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b738a7f755cea64e1894b34419551cc8aef039dbba4d771bc6fbcb6b8c5aad +size 338608384 diff --git a/Qwen2.5-0.5B-200K.i1-Q2_K_S.gguf b/Qwen2.5-0.5B-200K.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4cecbd6 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7d7efd069444f6e7efe2230fef76a914e1263743310db9a141cda60b147e86 +size 331049728 diff --git a/Qwen2.5-0.5B-200K.i1-Q3_K_L.gguf b/Qwen2.5-0.5B-200K.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9708632 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18bb70fc8aac04d931d14c84515cdbf408fcd42a47aea4af25c934e3b6d3faf +size 369359104 diff --git a/Qwen2.5-0.5B-200K.i1-Q3_K_M.gguf b/Qwen2.5-0.5B-200K.i1-Q3_K_M.gguf new file mode 100644 index 0000000..40c0908 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc6fe9721493822d30ea0b28e579ce0ffc98d899bbd700f21b8fa2b7cf23393 +size 355467520 diff --git a/Qwen2.5-0.5B-200K.i1-Q3_K_S.gguf b/Qwen2.5-0.5B-200K.i1-Q3_K_S.gguf new file mode 100644 index 0000000..84261e6 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ac1789f77d0fb690730a1c9489c60f8109ef9a0f31bbb53e36d1dd39121360 +size 338264320 diff --git a/Qwen2.5-0.5B-200K.i1-Q4_0.gguf b/Qwen2.5-0.5B-200K.i1-Q4_0.gguf new file mode 100644 index 0000000..3fac6bc --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d084e22f286ac2a524cbab18445bb22405ef8aefb5c7bb8d38f715577cf481b2 +size 352973056 diff --git a/Qwen2.5-0.5B-200K.i1-Q4_1.gguf b/Qwen2.5-0.5B-200K.i1-Q4_1.gguf new file mode 100644 index 0000000..01a606b --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7d9e1c09e71bc4ec301971d0e9f6a74bda8b3a733cff1d6a5df42b90fbcfff +size 374520064 diff --git a/Qwen2.5-0.5B-200K.i1-Q4_K_M.gguf b/Qwen2.5-0.5B-200K.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5594808 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c5f53bc81b2e31c2832956cb674c4f669050064bede36c889cc624173b7c9e +size 397808896 diff --git a/Qwen2.5-0.5B-200K.i1-Q4_K_S.gguf b/Qwen2.5-0.5B-200K.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a1ebc5e --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d745e69e0437d5cdd8bfc638f12be3276427ccb7037430353cef6f297cadf2a +size 385472768 diff --git a/Qwen2.5-0.5B-200K.i1-Q5_K_M.gguf b/Qwen2.5-0.5B-200K.i1-Q5_K_M.gguf new file mode 100644 index 0000000..1d5367c --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21e27584d5fc9f4c10ec807e14a408693c346980d4362778494c176b272d1e5 +size 420087040 diff --git a/Qwen2.5-0.5B-200K.i1-Q5_K_S.gguf b/Qwen2.5-0.5B-200K.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a109cc7 --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2035450c229b665c941c501a359949d96ea73c7516b418ec4a8f8556b8059e12 +size 412711168 diff --git a/Qwen2.5-0.5B-200K.i1-Q6_K.gguf b/Qwen2.5-0.5B-200K.i1-Q6_K.gguf new file mode 100644 index 0000000..affc94d --- /dev/null +++ b/Qwen2.5-0.5B-200K.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5bd15863f017bdbc9b83d0c44992c003f160b7cc35cd611a42b51ff0cc19d6 +size 505737472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..87e5b2d --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: prithivMLmods/Qwen2.5-0.5B-200K +datasets: +- HuggingFaceH4/ultrachat_200k +language: +- en +library_name: transformers +license: creativeml-openrail-m +quantized_by: mradermacher +tags: +- Qwen +- Qwen2.5 +- 0.5B +- Llama-cpp +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Qwen2.5-0.5B-200K + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-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/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-200K-i1-GGUF/resolve/main/Qwen2.5-0.5B-200K.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..c6dc705 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f30838e951a0d1274d2482d02779747f9a2a4b5ca81b30f92d0b2014a6efca9 +size 988597