commit ba6648d85526a59c79aa3b484d5f86b435a6fc21 Author: ModelHub XC Date: Sat May 30 11:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4d56c7e --- /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 +BitCPM4-CANN-0.5B-unquantized.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BitCPM4-CANN-0.5B-unquantized.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_M.gguf new file mode 100644 index 0000000..d606b5f --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843458c326b2f2c26228d69f8ccb42bec3e6db575c3c42fb19ae9f7307ae4dc8 +size 135486560 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_S.gguf new file mode 100644 index 0000000..c008115 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be45feed4554adf0f04c2f61b2255e62da41f41ba1e8fd4b217a9d696406334 +size 128040032 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_M.gguf new file mode 100644 index 0000000..8c4d4cd --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8422281dabfa877bee45696cfdab1bbc6742a42af2541a1147f09dde16d8d4e9 +size 173358176 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_S.gguf new file mode 100644 index 0000000..688cfb5 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1bda3a6b5a2ac93136878c8cdf9fae2e190585ede0f8b6af24fcbeb471c1e9 +size 163429472 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XS.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4576a38 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7a72cca675320501cc592fd87e585fbb3b356b3245de89e6d19f7241905feb +size 158612576 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XXS.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c5eadb2 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136b36b15873165842b1d58df732c1b0252333df62745751b788a2a7f497af9a +size 147897440 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_M.gguf new file mode 100644 index 0000000..767a3e7 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42f212e6c4befdec6892d054b9e2cc48c6aed5112ea16efe595dcb8e76a98d8 +size 223111072 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_S.gguf new file mode 100644 index 0000000..2db6258 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0ac564e5fed8d4f93848cac9652549f3f710b98ffa722dbfc7e88d18fd578e +size 218097568 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XS.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XS.gguf new file mode 100644 index 0000000..50d0efc --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffd70667e63156d6609ffcc60d35dafdad624fccc3d20a940bf3ed4d2a421fa +size 209692576 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XXS.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..7e35931 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06f54fa8a45c8345c346e9c954265bf58fdb5ce98402bf2d2aeeea4306a3272b +size 190856288 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_NL.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5e7b70b --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cd1e2f862af635c578aa073706cc67f29dbf925a16ec6936bac3e1e24fab80 +size 265701280 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_XS.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7ef5612 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6c37f388407c3663c3d3d1d021691092432e91dd6948c06fb2644593ec589c +size 254592928 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K.gguf new file mode 100644 index 0000000..2fee813 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346f24e5cf86e824afde6baa75378cdde8312358901f8d3415e4fc981026e00c +size 194774944 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6700481 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e95da88d44a42381960ca8b8a93dfc4bf191bcc88eb5f78576b12edff0ee89 +size 184944544 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_L.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f5a42d0 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa479155461f1e2777ee82356eaf810a5be06da0d390f3971d1e60e185f418a +size 250931104 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6aec7ad --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ed6dbc236c7f86b5288b7d2e623fe5b61f0dfd460dab12766cd77a0bea40c7 +size 235366304 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b9ba7c9 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c81b71f18bfc74b4c7bf54ec277e1a26943c308711450450d77521b554f1d85 +size 217679776 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q4_0.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_0.gguf new file mode 100644 index 0000000..af4eb96 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ebcebe4205f3cb423531807a1c35c239ebf3cce8a8e07b2de0c0b3f346704cb +size 266094496 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q4_1.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_1.gguf new file mode 100644 index 0000000..7e10728 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09e4f40b96d4b07d292986a4e0d6beb3c355e5077be0d6904943cca1bebf193 +size 287721376 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_M.gguf new file mode 100644 index 0000000..d704a3d --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f05ea5ba72455a2f4bece52f7d3e79fa3659c1dfd5b4b0a98f67f3454318590 +size 278689696 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e297a7f --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04581f14fe247ba25fc6b8bbaf603b6c49ccbe08ff48acc64bee713307b66f8 +size 266946464 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_M.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_M.gguf new file mode 100644 index 0000000..849a479 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1577b40abbacfbd358d43b279d76cd2e09b0a6839dc34c038e4edaf32c876a1a +size 317028256 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_S.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_S.gguf new file mode 100644 index 0000000..014b9f0 --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e55f2b96cddf40829dfee2010850c67aa1cc3ecbdf5bde4b8bc76c0d30086b4 +size 310134688 diff --git a/BitCPM4-CANN-0.5B-unquantized.i1-Q6_K.gguf b/BitCPM4-CANN-0.5B-unquantized.i1-Q6_K.gguf new file mode 100644 index 0000000..536219c --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2882c7825507fc05458e213efe71c2465ecd6dd44dbe9de34deb1f33fc9d191 +size 357762976 diff --git a/BitCPM4-CANN-0.5B-unquantized.imatrix.gguf b/BitCPM4-CANN-0.5B-unquantized.imatrix.gguf new file mode 100644 index 0000000..06195cc --- /dev/null +++ b/BitCPM4-CANN-0.5B-unquantized.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11c068fc00034a46b816822f51e028d35556b545af231c5fe263386628178af0 +size 1008928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0cde852 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: openbmb/BitCPM-CANN-0.5B-unquantized +language: +- zh +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/openbmb/BitCPM-CANN-0.5B-unquantized + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BitCPM4-CANN-0.5B-unquantized-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-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/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_S.gguf) | i1-IQ1_S | 0.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ1_M.gguf) | i1-IQ1_M | 0.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_S.gguf) | i1-IQ2_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ2_M.gguf) | i1-IQ2_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q2_K.gguf) | i1-Q2_K | 0.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_S.gguf) | i1-IQ3_S | 0.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ3_M.gguf) | i1-IQ3_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.4 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q4_0.gguf) | i1-Q4_0 | 0.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q4_1.gguf) | i1-Q4_1 | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BitCPM4-CANN-0.5B-unquantized-i1-GGUF/resolve/main/BitCPM4-CANN-0.5B-unquantized.i1-Q6_K.gguf) | i1-Q6_K | 0.5 | 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. + +