commit f78b225b7710f49b7c019cec4bdc95711f709086 Author: ModelHub XC Date: Fri May 15 02:49:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..713c322 --- /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 +Hemlock-Qwen2.5-Coder-14B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Hemlock-Qwen2.5-Coder-14B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_M.gguf new file mode 100644 index 0000000..54d39fa --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97525bb9c24d9603cbb6d55aaf0e747e2cfc07f46c0d0d15346a83a6a48a71a7 +size 3872309984 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_S.gguf new file mode 100644 index 0000000..7c5ac57 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88d84a95b7ce37b876d0f3fd739c3c820c5a2b437adcd08b95d4731e67ffb53 +size 3607995104 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_M.gguf new file mode 100644 index 0000000..df07424 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f61f7c1e81727d18e87a702ea0c777833976c68ec93ff8a346d76c889b9fd73 +size 5356147424 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_S.gguf new file mode 100644 index 0000000..7e2bb60 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ced571aee8cfecebfb281f72a31735b64acea39c7dc302b5d90d718278042b +size 5003727584 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XS.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..0dbed93 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe52f1c79714bd8d0883c24138a2c59ab0635e48e990f8fb8ac391fc1ecb5cfe +size 4704576224 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XXS.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a20b36d --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6743b746d69f076d3a1315ad14a6e04382b1863a9e1d4885c8b630594c9c4cfd +size 4312834784 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_M.gguf new file mode 100644 index 0000000..231327f --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0efdc271e45d1b1f8956ccb6a9274aa0c17ecce45a3452bdbcef644dcd03f1 +size 6916539104 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_S.gguf new file mode 100644 index 0000000..7fa6f80 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520b7bf510077ce7846f6836b2363b0e4ff2a9a4e0d2782c9b9fcff13934d0df +size 6693020384 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XS.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a63a9af --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6e6c011e132ccd1e8c843cbf5f12333539702ac30f5fe0c77e38f1672b2b7d +size 6383362784 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XXS.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4156e0a --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53251728e56eb957a30ec1f146766ef9463339276e8909827597b78c5aeb4567 +size 5946708704 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_NL.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..585dbb6 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98fdd17af97374b81d93e8d79142f0c850856cedc5fed3271421e93dc1272ff +size 8549184224 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_XS.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8884426 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68edfacd4050d0e47e02705ef8ec5db7aa45bc9e54ad5275d3c9cc5873fcf1e +size 8119841504 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K.gguf new file mode 100644 index 0000000..cfbcb94 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c106c4281243bc421ba80efec14cf83c03a1ed62a5789da34c32584c40145d44 +size 5770498784 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..49d8e5e --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fcde22175dc4e5122cf6a74637e5329ad2060386b08ed1a1521054f68463b6 +size 5397189344 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_L.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..37b3796 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfcfc2d9c252276d91089ca53f6ea2b6036db300108f2f94a1c40daa112212a5 +size 7924769504 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..94f775f --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f2bcf26da7774230b5c70c200db8da58bc4b0a7140e48f8d3509b0fed19303 +size 7339205344 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..de0ffe6 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784fa761e9f1e30d6734ebf52b0a38b2cd3a6fe07cbbd10a11a5efe029ad1c40 +size 6659597024 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q4_0.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_0.gguf new file mode 100644 index 0000000..3d93142 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a287f1a226b6624e1661947a858572f8841ba3971f5c667bd9f46296b6e8855 +size 8544269024 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q4_1.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_1.gguf new file mode 100644 index 0000000..b5f4ff6 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f69b891c3cc3d6d454878ab6acbfceb8ea1875c90d86fdc98bbe36ace1d1fb3 +size 9392141024 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..09c0f90 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ed92d3ea5ddb3a6603e98e5fe53df1667635e3946839d5b1dfa0f6f14b31c1 +size 8988111584 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..100f861 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e476dc2ffdc73c06ef757d7b3fb8ffdda8209151fac692719462c65495fefde +size 8573432544 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_M.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..579c71d --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7584ebc7c982318028cd132403e5995742e203db7308861549df571b5d2accd8 +size 10508874464 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_S.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9333efb --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594ab2692a9cee861e6ee7758c431af8acd0e01f2353b2f77ddb8a9a3c6935e3 +size 10266555104 diff --git a/Hemlock-Qwen2.5-Coder-14B.i1-Q6_K.gguf b/Hemlock-Qwen2.5-Coder-14B.i1-Q6_K.gguf new file mode 100644 index 0000000..073fcf5 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef175c7718dc35b72372bf3522249ed50ad96643503f31839cdbdb31996ffa5 +size 12124685024 diff --git a/Hemlock-Qwen2.5-Coder-14B.imatrix.gguf b/Hemlock-Qwen2.5-Coder-14B.imatrix.gguf new file mode 100644 index 0000000..de20506 --- /dev/null +++ b/Hemlock-Qwen2.5-Coder-14B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4111ccb831a8b135980207a29dff6221ce603314c6175b00be750850847e39 +size 8604128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cbab360 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: nbeerbower/Hemlock-Qwen2.5-Coder-14B +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-14B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hemlock-Qwen2.5-Coder-14B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-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-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hemlock-Qwen2.5-Coder-14B-i1-GGUF/resolve/main/Hemlock-Qwen2.5-Coder-14B.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. + +