commit 56b1d5a04cbc6352bcc77b4a51d5b1a18bb097c7 Author: ModelHub XC Date: Thu Oct 22 08:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-14B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..620ebb3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 +Qwen2.5-14B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-14B-Instruct.i1-IQ1_M.gguf b/Qwen2.5-14B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..410c541 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6307ff301efa92a56bc6892bdc4f0a1faf3f52bbc4c299aa88c1613c7388a5 +size 3872309792 diff --git a/Qwen2.5-14B-Instruct.i1-IQ1_S.gguf b/Qwen2.5-14B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..d5ff1ea --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f78432c5c208ed94cd6d75a74539aeb529ef0da3ad36942556ca83cdeec032c +size 3607994912 diff --git a/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf b/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..1aa8e50 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffcbbd97dca87f825b8b33cea05c9bd77cff11404110c39039326c67cde1e3d +size 5356147232 diff --git a/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf b/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..8421d0c --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9e21d76e26eda853fd94ec1b3689e8372acc5199af016fde8c5a6508ccc9c0 +size 5003727392 diff --git a/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf b/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b93923a --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571e3e38eb74992b41f2cc5c0e2aecfca84e97e6b3f83e9bea2c7a1d30962e3f +size 4704576032 diff --git a/Qwen2.5-14B-Instruct.i1-IQ2_XXS.gguf b/Qwen2.5-14B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..39db706 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad49eda7903cdc2a1db8a71455532dcfeb90a296a7e7a86a57e94a4ac4951f8 +size 4312834592 diff --git a/Qwen2.5-14B-Instruct.i1-IQ3_M.gguf b/Qwen2.5-14B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..c9e6657 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa4976d188c318eb0ad3e5557e3498683429edb76302937ca4120c6128dd39d5 +size 6916538912 diff --git a/Qwen2.5-14B-Instruct.i1-IQ3_S.gguf b/Qwen2.5-14B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..2e39ead --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba68353891bf67d2b0cc72fcef05e31081b114853525df74ef060f7e0e9e790 +size 6693020192 diff --git a/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf b/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d8eb9f1 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2909c498c463816d5f15789c9f0ffcf4b002b957bed51a74294b8fed77c7b5 +size 6383362592 diff --git a/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf b/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fc5b2e6 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215691c95877be8279f882b40fc0d8ecc30203eb8d11c05b8c1a4604d15961ae +size 5946708512 diff --git a/Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf b/Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..92f618c --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:255b7e3a101f5038568f19acd3a644b2deac9936da93cbfa72d75bdda1b112dd +size 8549184032 diff --git a/Qwen2.5-14B-Instruct.i1-IQ4_XS.gguf b/Qwen2.5-14B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..af1f11f --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d2f9154ffda0a4d9ffaf5a3b955e3b4e012e866b60c879fc082a2a463520dcf +size 8119841312 diff --git a/Qwen2.5-14B-Instruct.i1-Q2_K.gguf b/Qwen2.5-14B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..a1ee19e --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be22b18f176eb1255a2d60ba63edcfdf4b98fddf1cc21584b9a31593269a3b7 +size 5770498592 diff --git a/Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf b/Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f78ba46 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2f886d1fe61796a5a01981dab77cd435e74305377daebf5bd1ffdad4a0a9be +size 5397189152 diff --git a/Qwen2.5-14B-Instruct.i1-Q3_K_L.gguf b/Qwen2.5-14B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2201f98 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d0c9ebca5044bb4011723b5f2fcc2de618f6e36c28d94a791e1df1cac29474 +size 7924769312 diff --git a/Qwen2.5-14B-Instruct.i1-Q3_K_M.gguf b/Qwen2.5-14B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c1dfbf4 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160f13320bcdce16792f0d27c43229d3d8a69bf33e09cd67bdc9ac4f74945abe +size 7339205152 diff --git a/Qwen2.5-14B-Instruct.i1-Q3_K_S.gguf b/Qwen2.5-14B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f464197 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d985ac292378fed4f45eb9d6f1c293eec7812119e0dcca8b7ef866b36f29cb87 +size 6659596832 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_0.gguf b/Qwen2.5-14B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..2a4fffd --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef8fb8cf782f72ebcb974e9938988866436afff4240a7cfa95d3052819823fd +size 8544268832 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_0_4_4.gguf b/Qwen2.5-14B-Instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..d25d00c --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598fa20ad61db63452ba85df72a3556ffb8ff9386077718d7dc713bf664cb6e9 +size 8517726752 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf b/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..c8ca57a --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8392aa26cc9d04afa95488e4f2624918f6b2f5c9f6c5eb33d916c6160c25eb +size 8517726752 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf b/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..87b4685 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed11585c1733a4c2155c96a57e48dab8c16d77b15807b540486870e18d77d69a +size 8517726752 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_1.gguf b/Qwen2.5-14B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..dade0f0 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5514a670b66db3020a19881b6276cec8a712875563339b55fc4a2a6631bc388 +size 9392140832 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf b/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..66e73fa --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be066f31367c03ddf5444d9bfaee6b0c010ae4b0b14dd3afaf61a94723180ad +size 8988111392 diff --git a/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf b/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..ca6dfba --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355610ce4e0b8a4365976419a03522b185fad3ae3ab8a83a9e71a5dfa74e9b1d +size 8573432352 diff --git a/Qwen2.5-14B-Instruct.i1-Q5_0.gguf b/Qwen2.5-14B-Instruct.i1-Q5_0.gguf new file mode 100644 index 0000000..44737cf --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93e955f8b41e9f74b584ef4526e6a2cee06321ce55ade36ad7615c28cf19b5c +size 10293096992 diff --git a/Qwen2.5-14B-Instruct.i1-Q5_1.gguf b/Qwen2.5-14B-Instruct.i1-Q5_1.gguf new file mode 100644 index 0000000..71ec4ff --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906d6cbcd18ce8f761e3dc178e78b7246d102286a99aef751e70b0881801cf92 +size 11140968992 diff --git a/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf b/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..05b11b2 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e3f0b7c1d21e6f303625c84a9755ef0e2e4500b968cdb92416be41916ebcc7 +size 10508874272 diff --git a/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf b/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4b11950 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fa007ea20910a4cf62e93420f61f884c71d85924d75a19cefbce0f2c9c44a6 +size 10266554912 diff --git a/Qwen2.5-14B-Instruct.i1-Q6_K.gguf b/Qwen2.5-14B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..9eda798 --- /dev/null +++ b/Qwen2.5-14B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb22df7acaf2fb8e7f72864a61c08dc10054fa0156bbc5d8dfcdeb671029006 +size 12124684832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0b382a --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Qwen/Qwen2.5-14B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-14B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-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/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_0.gguf) | i1-Q5_0 | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q5_1.gguf) | i1-Q5_1 | 11.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-14B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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..5ce0e85 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4799852c8f1c4f19aeb8d1550c99b74aabd95e6e46a75307a296b6f66682f282 +size 8563597