commit 90a01c4115e0c459285ff7722e664875af371291 Author: ModelHub XC Date: Tue May 19 17:19:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deepthink-Reasoning-14B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5617dc8 --- /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 +Deepthink-Reasoning-14B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Deepthink-Reasoning-14B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deepthink-Reasoning-14B.i1-IQ1_M.gguf b/Deepthink-Reasoning-14B.i1-IQ1_M.gguf new file mode 100644 index 0000000..d0cb0ea --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16a8eb5af8baeeb5b32094d4304d7845816d05c25bc5365b62166698b783a18 +size 3872310720 diff --git a/Deepthink-Reasoning-14B.i1-IQ1_S.gguf b/Deepthink-Reasoning-14B.i1-IQ1_S.gguf new file mode 100644 index 0000000..f28763a --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b89af0a065f6fc82889c1173aff357f5081625823ccbe89124b83822a045b3 +size 3607995840 diff --git a/Deepthink-Reasoning-14B.i1-IQ2_M.gguf b/Deepthink-Reasoning-14B.i1-IQ2_M.gguf new file mode 100644 index 0000000..61f555b --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb7cb9b73553b76efb9e04aed4c80bc334ba481e486e8ee8991d1e8c02fa9aff +size 5356148160 diff --git a/Deepthink-Reasoning-14B.i1-IQ2_S.gguf b/Deepthink-Reasoning-14B.i1-IQ2_S.gguf new file mode 100644 index 0000000..40f0baa --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0251d2a4f09cfb3112377743849087ac394abd0aad77d45d15a7bca8069375 +size 5003728320 diff --git a/Deepthink-Reasoning-14B.i1-IQ2_XS.gguf b/Deepthink-Reasoning-14B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bf67607 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99169bfe4c81091f732a90bc0f5c14bcead0e1e7ca9ba48a711facf9fe5b3c32 +size 4704576960 diff --git a/Deepthink-Reasoning-14B.i1-IQ2_XXS.gguf b/Deepthink-Reasoning-14B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b7a7258 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f57951f7862a8f72b44e37269ebb545b5abd630cd38dc21c2f43dc8357b7ac2 +size 4312835520 diff --git a/Deepthink-Reasoning-14B.i1-IQ3_M.gguf b/Deepthink-Reasoning-14B.i1-IQ3_M.gguf new file mode 100644 index 0000000..b239290 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49aae3e498dcb95a3d61ea6349e65e2bc29485efbc948a00e5c46dad15eec61b +size 6916539840 diff --git a/Deepthink-Reasoning-14B.i1-IQ3_S.gguf b/Deepthink-Reasoning-14B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1eedc6f --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca46dc18e71aad275b3068c29bbc9298484b84dfca1ede947b9fa4f78fff88c6 +size 6693021120 diff --git a/Deepthink-Reasoning-14B.i1-IQ3_XS.gguf b/Deepthink-Reasoning-14B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a55554e --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3fafee4d1df7a8718a128cbbcad20cfd53c3f325735834b350cdcd15e003eb3 +size 6383363520 diff --git a/Deepthink-Reasoning-14B.i1-IQ3_XXS.gguf b/Deepthink-Reasoning-14B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..860d530 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae077fe59fc3f449f03dc42cf90b712d2c32bed97ab3b26c88a58b91b98765e5 +size 5946709440 diff --git a/Deepthink-Reasoning-14B.i1-IQ4_NL.gguf b/Deepthink-Reasoning-14B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..39893e1 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7d95f0eccabc0b92413b4b41f37992439522b7d20744e4b621036453d2928f +size 8549184960 diff --git a/Deepthink-Reasoning-14B.i1-IQ4_XS.gguf b/Deepthink-Reasoning-14B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c8abd64 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762b103eff1b1370debed2af571f8fa399192c8062c541f9aa03313e7cf213d5 +size 8119842240 diff --git a/Deepthink-Reasoning-14B.i1-Q2_K.gguf b/Deepthink-Reasoning-14B.i1-Q2_K.gguf new file mode 100644 index 0000000..6d588b4 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc431d310deebcbf0a17bec8e76da0cb9e3a76bb9873c17b4d37aa1b67fd7e1 +size 5770499520 diff --git a/Deepthink-Reasoning-14B.i1-Q2_K_S.gguf b/Deepthink-Reasoning-14B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ee71ecb --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6795e973f64d3567d41dc460e5de2d638ac268b4f078c4ca47b697dbeb509374 +size 5397190080 diff --git a/Deepthink-Reasoning-14B.i1-Q3_K_L.gguf b/Deepthink-Reasoning-14B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c2ca27c --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e2cd80fe35ee7d8ecd68527e2146e7a63144b4de3c02baf5f2ca55db899ca0 +size 7924770240 diff --git a/Deepthink-Reasoning-14B.i1-Q3_K_M.gguf b/Deepthink-Reasoning-14B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c5cc735 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31aa3e44439d0b45152ff17ab7227a053a50c2f6dc7c7dca77c198c2de869c82 +size 7339206080 diff --git a/Deepthink-Reasoning-14B.i1-Q3_K_S.gguf b/Deepthink-Reasoning-14B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3ee4436 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f23f909c1be5458be02e13cba9c70b23d7acb4e704923e3d66b3afdf3d039be +size 6659597760 diff --git a/Deepthink-Reasoning-14B.i1-Q4_0.gguf b/Deepthink-Reasoning-14B.i1-Q4_0.gguf new file mode 100644 index 0000000..33b673f --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80137692ce0c86d0e2fa3d920ca7f9d31159dc4ff031d4ea35f647743dbebc71 +size 8544269760 diff --git a/Deepthink-Reasoning-14B.i1-Q4_1.gguf b/Deepthink-Reasoning-14B.i1-Q4_1.gguf new file mode 100644 index 0000000..9a8a0ae --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226b9c0b2a4b43a9e4aa1d35f14b6e36f2a5932c4b1962bc4f58ef2940acf6df +size 9392141760 diff --git a/Deepthink-Reasoning-14B.i1-Q4_K_M.gguf b/Deepthink-Reasoning-14B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b3c274f --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193f4a72265548b56876f397f04b59f97e625bc87c0ea0d818d2890f88c7c312 +size 8988112320 diff --git a/Deepthink-Reasoning-14B.i1-Q4_K_S.gguf b/Deepthink-Reasoning-14B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8698173 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6b4bd6ba9fc56c3e4880ebb18e1eb7608b657e6fbbc9049548b50830c42d64 +size 8573433280 diff --git a/Deepthink-Reasoning-14B.i1-Q5_K_M.gguf b/Deepthink-Reasoning-14B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c2ac70b --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b5729398f327c70ef3cc217ee93efb0f3a1f06ca4296eb9d624ebc784ad633 +size 10508875200 diff --git a/Deepthink-Reasoning-14B.i1-Q5_K_S.gguf b/Deepthink-Reasoning-14B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4c88cc7 --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7c2c9fdc4149593cc6bdfb0b54fc9357dbec382f3b503b7b51b107c22eb9ae +size 10266555840 diff --git a/Deepthink-Reasoning-14B.i1-Q6_K.gguf b/Deepthink-Reasoning-14B.i1-Q6_K.gguf new file mode 100644 index 0000000..08c57fd --- /dev/null +++ b/Deepthink-Reasoning-14B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bbd0abaf50f58b650bf03644f59b3d075fef6092590321f848a3d7265cf2b3 +size 12124685760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..998840d --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: prithivMLmods/Deepthink-Reasoning-14B +datasets: +- prithivMLmods/Math-Solve +- AI-MO/NuminaMath-CoT +- amphora/QwQ-LongCoT-130K +- amphora/QwQ-LongCoT-130K-2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Math +- text-generation-inference +- Deep-think +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Deepthink-Reasoning-14B + + +static quants are available at https://huggingface.co/mradermacher/Deepthink-Reasoning-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/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-14B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deepthink-Reasoning-14B-i1-GGUF/resolve/main/Deepthink-Reasoning-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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..10181a6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e702ce21a365aa6f68ddf50bd9e57c1b0f489bbb2fa9a18b5c433efe6d976d +size 8563597