commit e2b3f6ef533e27f862c840672ded66a39b0da03d Author: ModelHub XC Date: Wed May 20 14:00:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeLlama3.2-3B-1225-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39ca50b --- /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 +CodeLlama3.2-3B-1225.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama3.2-3B-1225.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama3.2-3B-1225.i1-IQ1_M.gguf b/CodeLlama3.2-3B-1225.i1-IQ1_M.gguf new file mode 100644 index 0000000..e043188 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0beed557c9fb1830165d40c8271ff41e14a3941848a29c2524f65e14f4d853a +size 924193568 diff --git a/CodeLlama3.2-3B-1225.i1-IQ1_S.gguf b/CodeLlama3.2-3B-1225.i1-IQ1_S.gguf new file mode 100644 index 0000000..9a2afe8 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7328a2a58736d4f23b614a887495a757623aa4a4729f8fc868da13034974545 +size 868160288 diff --git a/CodeLlama3.2-3B-1225.i1-IQ2_M.gguf b/CodeLlama3.2-3B-1225.i1-IQ2_M.gguf new file mode 100644 index 0000000..6a44e56 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8c51bf137ef94bb144ac2dc1d22809797cca3aff24372e4537c011b5a009d1 +size 1229034272 diff --git a/CodeLlama3.2-3B-1225.i1-IQ2_S.gguf b/CodeLlama3.2-3B-1225.i1-IQ2_S.gguf new file mode 100644 index 0000000..2588293 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d8b35f093fbf96ec2ee18ac84e532e772a860f8862ae47d16558229285dc05 +size 1154323232 diff --git a/CodeLlama3.2-3B-1225.i1-IQ2_XS.gguf b/CodeLlama3.2-3B-1225.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e9df293 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e2ce7419576f889e249be4e36f805c0b08b9f7edcbfad001f1f1ea77497d6f +size 1100550944 diff --git a/CodeLlama3.2-3B-1225.i1-IQ2_XXS.gguf b/CodeLlama3.2-3B-1225.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e7a3b3b --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1224e9eb2b01fd5e20609c7372e5d0f04a19904b9001d8710f82c4c75a13e8f2 +size 1017582368 diff --git a/CodeLlama3.2-3B-1225.i1-IQ3_M.gguf b/CodeLlama3.2-3B-1225.i1-IQ3_M.gguf new file mode 100644 index 0000000..2764d16 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a20d4a4f2aa3311e1f6034c1c086b8cd7918ee2419f91ded683c878c6bb16e +size 1599671072 diff --git a/CodeLlama3.2-3B-1225.i1-IQ3_S.gguf b/CodeLlama3.2-3B-1225.i1-IQ3_S.gguf new file mode 100644 index 0000000..970041d --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ff479f36a2655946e024977b3a79967ad1374d3c1ef6bc7e1d6ba5f04e93863 +size 1542851360 diff --git a/CodeLlama3.2-3B-1225.i1-IQ3_XS.gguf b/CodeLlama3.2-3B-1225.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0a92165 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc35748558b55610723ce288cccbe19c9c6ffacadd2ff5acfc52498a6c68abf +size 1476791072 diff --git a/CodeLlama3.2-3B-1225.i1-IQ3_XXS.gguf b/CodeLlama3.2-3B-1225.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..00f375e --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367b5e55379cbc0e1a6e88e6410df8751d1ce3ba8e1a7025085b0c5804d1de58 +size 1348768544 diff --git a/CodeLlama3.2-3B-1225.i1-IQ4_NL.gguf b/CodeLlama3.2-3B-1225.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fa3fc8e --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8ba75259a794888cab64388dc581c6adc824f0d51e2a35617e5f5b15adb2f3 +size 1917192992 diff --git a/CodeLlama3.2-3B-1225.i1-IQ4_XS.gguf b/CodeLlama3.2-3B-1225.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e1cfd72 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367e4051103feab76efab45610b651e3f5bc31898f23d74599c3f7b534644200 +size 1829112608 diff --git a/CodeLlama3.2-3B-1225.i1-Q2_K.gguf b/CodeLlama3.2-3B-1225.i1-Q2_K.gguf new file mode 100644 index 0000000..a6dc04f --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d24c5829424b994fa325a2b769a8f77c2498ee63cf19c7ef90756c41855fab +size 1363938080 diff --git a/CodeLlama3.2-3B-1225.i1-Q2_K_S.gguf b/CodeLlama3.2-3B-1225.i1-Q2_K_S.gguf new file mode 100644 index 0000000..929aab5 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ab51c79d36f857b7fdd7c4990faa1ce8e069332ef33ac5036acac4a184a65d +size 1274284832 diff --git a/CodeLlama3.2-3B-1225.i1-Q3_K_L.gguf b/CodeLlama3.2-3B-1225.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3cf4030 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9489f818be4423146f3c505c36e61532a15cfa27112fdaca1d990bd6e05de68c +size 1815350048 diff --git a/CodeLlama3.2-3B-1225.i1-Q3_K_M.gguf b/CodeLlama3.2-3B-1225.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0c4d04b --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49c2f3cba6541b1cc84d5d2d7c88470aa3de405d9b63b0f3d697474412a46bd +size 1687161632 diff --git a/CodeLlama3.2-3B-1225.i1-Q3_K_S.gguf b/CodeLlama3.2-3B-1225.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6199d95 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5710342951682ccc8b28444abfbe78ff93ccca27689db7d3b3a9b7c8cc7e16f +size 1542851360 diff --git a/CodeLlama3.2-3B-1225.i1-Q4_0.gguf b/CodeLlama3.2-3B-1225.i1-Q4_0.gguf new file mode 100644 index 0000000..9bc0dcb --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3c578bd8bacb5ee2a934819008532c72eb574c30928a8cc503cfce9037d007 +size 1921911584 diff --git a/CodeLlama3.2-3B-1225.i1-Q4_1.gguf b/CodeLlama3.2-3B-1225.i1-Q4_1.gguf new file mode 100644 index 0000000..22487d9 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52b46a35efd335c7050260651ec1fd55fbd1eef3a17dd318f269c62e8b82150 +size 2093353760 diff --git a/CodeLlama3.2-3B-1225.i1-Q4_K_M.gguf b/CodeLlama3.2-3B-1225.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ec8a366 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4820e2160ff9bc1e403d89df3152c749669cc9e869257aa2186b769ca195df38 +size 2019380000 diff --git a/CodeLlama3.2-3B-1225.i1-Q4_K_S.gguf b/CodeLlama3.2-3B-1225.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8571170 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45339d3ffcbc7faada943de3b96b17f7e68bcef46dea39bdfb6d27a4d33f091b +size 1928203040 diff --git a/CodeLlama3.2-3B-1225.i1-Q5_K_M.gguf b/CodeLlama3.2-3B-1225.i1-Q5_K_M.gguf new file mode 100644 index 0000000..89b36d1 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3657f2b9150a7da276c43751607a9f4bfc49fe694c1b531ce67c34bb81ec2d13 +size 2322156320 diff --git a/CodeLlama3.2-3B-1225.i1-Q5_K_S.gguf b/CodeLlama3.2-3B-1225.i1-Q5_K_S.gguf new file mode 100644 index 0000000..367d6fc --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50304aa33c28016de766645bcc1d1867db897caa0807843cfbcc4e9b83ae5202 +size 2269514528 diff --git a/CodeLlama3.2-3B-1225.i1-Q6_K.gguf b/CodeLlama3.2-3B-1225.i1-Q6_K.gguf new file mode 100644 index 0000000..17fe2f9 --- /dev/null +++ b/CodeLlama3.2-3B-1225.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2f5ab7d1e7052652d084cd778d7d674650eff8038312baa453fa39791a149d +size 2643856160 diff --git a/CodeLlama3.2-3B-1225.imatrix.gguf b/CodeLlama3.2-3B-1225.imatrix.gguf new file mode 100644 index 0000000..93c720d --- /dev/null +++ b/CodeLlama3.2-3B-1225.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c18c3147937a4509600e6a2d02c34a5a0601217ab744cbf7a80a1563cbc59b +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..57deca6 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +--- +base_model: theprint/CodeLlama3.2-3B-1225 +datasets: +- theprint/MultiRoundConvos-Code-JS-HTML-CSS-Python +- theprint/VanRossum-GPT +- ajibawa-2023/Python-Code-23k-ShareGPT +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/theprint/CodeLlama3.2-3B-1225 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CodeLlama3.2-3B-1225-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-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/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama3.2-3B-1225-i1-GGUF/resolve/main/CodeLlama3.2-3B-1225.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. + +