commit d8d9fe4d0654f3cd2baf3e38b54c7796bc95ccb2 Author: ModelHub XC Date: Wed May 13 18:56:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1370600 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Hemlock-Qwen2.5-Coder-32B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-32B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_M.gguf new file mode 100644 index 0000000..19e55b0 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10fc5c568322faa02b64d0bb80e7fcdef0f8fbed6b11a248c03d9a5389db4483 +size 7932161504 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_S.gguf new file mode 100644 index 0000000..aa33b7d --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70a507c8d5bfdb57addb8fb7d837e33811fe3e4aaf177a25e07ce3c594994d5 +size 7274507744 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_M.gguf new file mode 100644 index 0000000..240980f --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707df3f0b743429da6822214c5e9cb6355b6645dc0c8ae48ea3b383fc6c60bda +size 11264441824 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_S.gguf new file mode 100644 index 0000000..780754b --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882ae16545cfcbc2ec992d59cb1ec0458a54b0f6cceeed0ceeff189b07f1e684 +size 10387570144 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XS.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e27867f --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c739b8c0bc1e45cab442c49fa124821820d85a6e4d9cf86f610e91b2fff9287c +size 9957551584 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XXS.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bd2911f --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1982fdf032cf8575734fda87beda028bf1206f3cdbf0f662df9dcddf34a2d088 +size 9028251104 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_M.gguf new file mode 100644 index 0000000..4b5da23 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a95cfa3668b26d2962c861f1fb354f2e10820a0e0ada4e3833d567ff371ea1 +size 14810123744 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_S.gguf new file mode 100644 index 0000000..3fafbdc --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:decb12ae0d1e16fc47b0f1f9b9243135276ebd81aa770277344d7a931f8164ac +size 14436896224 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XS.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bfe13c1 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5751964399d9a335196618969d1c473b1636f73cc34dfaf3a3c333e143cc38ef +size 13705514464 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XXS.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..96b0efe --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c44c4eb285f74d2b8f76634053af5601de1f05cb94faf1c5d2b11b5417ad98 +size 12839271904 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-IQ4_XS.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8aa66e4 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6727edba8c6e56da689f06c124e5d7bd801a182d1229be3b0f19690d14f3f3b7 +size 17693154784 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K.gguf new file mode 100644 index 0000000..ae87e7e --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9e9bd255df8b45dfd32085473b55503e3149718d0a351fedb777d00440181a +size 12313099744 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..74284fe --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eac865f293056b8e8c21ecc83b6fc56684dbe8119175282a45db8c03e2ab5c4 +size 11488001504 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_L.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c1e0d23 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a0091e7a35d8e36bffc6260f0159d55c0a9ba9c7016b5d247d3dad54ee86db +size 17247079904 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f0e8a0d --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2255bc088dd64506cca0d6d718fe8c7aae293d97fac6db6a25ae0eb7b685a87b +size 15935049184 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c6b1239 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80acbfff7d07713f42938a0b93b58d5a7edb7434147b02476e2e61bc50ae1fc +size 14392331744 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q4_0.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_0.gguf new file mode 100644 index 0000000..43c9acf --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ff0d50e253b0269e622b5195f9b2e43dae44fe518ae7b66b44980577587826 +size 18711010784 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q4_1.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_1.gguf new file mode 100644 index 0000000..2705837 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3e0fafa2a925418b5995864326cd4eee7faafffdaf4a022226eb0bc3f70bc1f +size 20639243744 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..2e87564 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97feaba91dcb38535970598b235b89bd73cc6386948f3f293e7d0785867d6acc +size 19851337184 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7e5f077 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c57c5879c70ca8ea2f704303b4478c0550f342c09166aee57293dee33cf5eb9 +size 18784411104 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_M.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..01577b3 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731cf2cd993516a7b5c45122f0577a6758a655e1bd9649006698b2aa4668b09c +size 23262158304 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_S.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2229f8a --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed2448e561b092f91054309e4700eaf2510b5e984fbcdff3ae99ed7d56c8046 +size 22638255584 diff --git a/Hemlock-Qwen2.5-Coder-32B.i1-Q6_K.gguf b/Hemlock-Qwen2.5-Coder-32B.i1-Q6_K.gguf new file mode 100644 index 0000000..8867f9b --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c29f14d973c9a9c7b05101c07497a89f213cc5173ca792cc5410489b95069d +size 26886155744 diff --git a/Hemlock-Qwen2.5-Coder-32B.imatrix.gguf b/Hemlock-Qwen2.5-Coder-32B.imatrix.gguf new file mode 100644 index 0000000..6c7507a --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-32B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2785ef893c353a2e09c3410cae0781bab316b53c6072549e2150a8bb245f4d76 +size 15011072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4182a93 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: nbeerbower/Hemlock-Qwen2.5-Coder-32B +datasets: +- nbeerbower/hemlock-sft-v0.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/Hemlock-Qwen2.5-Coder-32B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hemlock-Qwen2.5-Coder-32B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-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/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-32B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-32B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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. + +