commit c09a645d518a886dfdccd6f6cf8d5fd5c5cd8aa4 Author: ModelHub XC Date: Tue May 12 01:38:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-COT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b855694 --- /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 +Llama-3.2-3B-COT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-COT.i1-IQ1_M.gguf b/Llama-3.2-3B-COT.i1-IQ1_M.gguf new file mode 100644 index 0000000..1b13352 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efd3b68de3600181e2c50e2f31bd386491cd4db9b5295a52115297154046bb39 +size 924193504 diff --git a/Llama-3.2-3B-COT.i1-IQ1_S.gguf b/Llama-3.2-3B-COT.i1-IQ1_S.gguf new file mode 100644 index 0000000..78e9b07 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8ebab66d4e2bf5e8c268ec6086f3f0b85ebe1628d8ce452dc4a38990a8ca69 +size 868160224 diff --git a/Llama-3.2-3B-COT.i1-IQ2_M.gguf b/Llama-3.2-3B-COT.i1-IQ2_M.gguf new file mode 100644 index 0000000..117b62a --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8093d0eedaa300f0e3ef07a0b9a109f57bb0ee990b47637d91ff7946e7b70659 +size 1229034208 diff --git a/Llama-3.2-3B-COT.i1-IQ2_S.gguf b/Llama-3.2-3B-COT.i1-IQ2_S.gguf new file mode 100644 index 0000000..a321daf --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ea6887e5f4593b003ea8b9abdf6aaf62fa91f847053beb4533ebdddb3a6bb5 +size 1154323168 diff --git a/Llama-3.2-3B-COT.i1-IQ2_XS.gguf b/Llama-3.2-3B-COT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..473375f --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22f2e1abaa3a0ef5f862a32242510c8666b1ec26853adf717cbb9e627c837c6 +size 1100550880 diff --git a/Llama-3.2-3B-COT.i1-IQ2_XXS.gguf b/Llama-3.2-3B-COT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..85d598d --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f331f2c6bdd87a9b749788e87d1eea5ea500443489a22ba7b6b2ee60d00a2e2c +size 1017582304 diff --git a/Llama-3.2-3B-COT.i1-IQ3_M.gguf b/Llama-3.2-3B-COT.i1-IQ3_M.gguf new file mode 100644 index 0000000..b5fe288 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06fcad1d778296bb88feb6f91d45019aa02dbc0c8a42295eedf1a8dc589e733 +size 1599671008 diff --git a/Llama-3.2-3B-COT.i1-IQ3_S.gguf b/Llama-3.2-3B-COT.i1-IQ3_S.gguf new file mode 100644 index 0000000..0f379ea --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09f3dfc071555f848112f5c59d28f39dffe644a108a69b52d39bc1ce533009b +size 1542851296 diff --git a/Llama-3.2-3B-COT.i1-IQ3_XS.gguf b/Llama-3.2-3B-COT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f0ea170 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6e7e02cf5358e2bc1f1ae3e450412622331188ede1d1afa59423ca169697a4 +size 1476791008 diff --git a/Llama-3.2-3B-COT.i1-IQ3_XXS.gguf b/Llama-3.2-3B-COT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..858bbbd --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3054a7b54e3d33a63a82881f3ec0bc70b1ead8dce4dfcc76551b3e9a0217f55e +size 1348768480 diff --git a/Llama-3.2-3B-COT.i1-IQ4_XS.gguf b/Llama-3.2-3B-COT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c07177b --- /dev/null +++ b/Llama-3.2-3B-COT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c13d7fc7c7f125568c02465e08703b1cf5d585a1dcfc58c3146dc750caf9b4d +size 1829112544 diff --git a/Llama-3.2-3B-COT.i1-Q2_K.gguf b/Llama-3.2-3B-COT.i1-Q2_K.gguf new file mode 100644 index 0000000..65a87a7 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248f2fb4a2d098219c5726fa29f279c8d55bb569776b9d6f19a0d8ab4f176ace +size 1363938016 diff --git a/Llama-3.2-3B-COT.i1-Q3_K_L.gguf b/Llama-3.2-3B-COT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d229e34 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936c5c25d5bf448d03f742194cbc92aa188746c4db950aada6a8c0b682d968af +size 1815349984 diff --git a/Llama-3.2-3B-COT.i1-Q3_K_M.gguf b/Llama-3.2-3B-COT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1e33671 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad2b78ae985d6dbbe0f37ee66b03c98a130a56a43af2acaa8ee7aaad42f33f8 +size 1687161568 diff --git a/Llama-3.2-3B-COT.i1-Q3_K_S.gguf b/Llama-3.2-3B-COT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3fd71a7 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a37b29e078b86a3c37ceb0195667f70acd2980f6f0506ddea8ebf4a39bdc9c +size 1542851296 diff --git a/Llama-3.2-3B-COT.i1-Q4_0.gguf b/Llama-3.2-3B-COT.i1-Q4_0.gguf new file mode 100644 index 0000000..b1d1cca --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ba3c1afcddf20ddaa662576f10c5c818449f1a68a79c7ed8e7d61666824dbf +size 1921911520 diff --git a/Llama-3.2-3B-COT.i1-Q4_0_4_4.gguf b/Llama-3.2-3B-COT.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..8ace22f --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fada3c4086323817273e1b57bbe790b0a9e386d4fad3d0995d8f1b483ae2697 +size 1917192928 diff --git a/Llama-3.2-3B-COT.i1-Q4_0_4_8.gguf b/Llama-3.2-3B-COT.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..95f587e --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37a93fd8ec67e1a6229227eb1a04685f507604bf9c978ef2e06c8e1361e939b +size 1917192928 diff --git a/Llama-3.2-3B-COT.i1-Q4_0_8_8.gguf b/Llama-3.2-3B-COT.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..cad5b69 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe419520fe3bbc51be3087cea95cac151eedf2c9ae0fa805bd9d595f797349f +size 1917192928 diff --git a/Llama-3.2-3B-COT.i1-Q4_K_M.gguf b/Llama-3.2-3B-COT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6537ec1 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1004a0758b30d39ca2208ee5895c84441817b16349aa15065a28dc38a6edea4 +size 2019379936 diff --git a/Llama-3.2-3B-COT.i1-Q4_K_S.gguf b/Llama-3.2-3B-COT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e521e55 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f91f1bc81e44e03a61da5d15f3dd490cd7fcee4e26b9f3ed174915afdfda36 +size 1928202976 diff --git a/Llama-3.2-3B-COT.i1-Q5_K_M.gguf b/Llama-3.2-3B-COT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..53b3baf --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:603914e8f7f5ee35304ab0091ad35d35b89f237284c7a12bf6cf86f28ccc93d6 +size 2322156256 diff --git a/Llama-3.2-3B-COT.i1-Q5_K_S.gguf b/Llama-3.2-3B-COT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..224c8c9 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a670d72453ae18e257d3c6ccab414f62f5a5221fc17c671d07dc53feb8035f +size 2269514464 diff --git a/Llama-3.2-3B-COT.i1-Q6_K.gguf b/Llama-3.2-3B-COT.i1-Q6_K.gguf new file mode 100644 index 0000000..145b835 --- /dev/null +++ b/Llama-3.2-3B-COT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92603645afb0ab3117704747ca146dc41de32e73ce815a68f1199f31f79ab228 +size 2643856096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e97ee1e --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: ericflo/Llama-3.2-3B-COT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama-3.2 +- thought-chain +- instruction-finetuning +- transformers +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ericflo/Llama-3.2-3B-COT + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-COT-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-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.0 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.0 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-i1-GGUF/resolve/main/Llama-3.2-3B-COT.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..d7401e2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544bac86ce0fbc19fdad9ab99b8d9f154f795b8f8ee9b8d3c479032f4c2fb9ac +size 2988377