commit cda7587c9a5ebe53844a22dc1e3425765bfe50ab Author: ModelHub XC Date: Sun May 10 06:55:01 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRPO-Think-14B-8k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f238cf2 --- /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 +GRPO-Think-14B-8k.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-Think-14B-8k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRPO-Think-14B-8k.i1-IQ1_M.gguf b/GRPO-Think-14B-8k.i1-IQ1_M.gguf new file mode 100644 index 0000000..6a8843c --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a4398aa7ccd5192bcf97ec01c94083dbbe6f9d59f4816cecbb958d742a5529a +size 3872309792 diff --git a/GRPO-Think-14B-8k.i1-IQ1_S.gguf b/GRPO-Think-14B-8k.i1-IQ1_S.gguf new file mode 100644 index 0000000..a13f380 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26820517c6e87595ac4bd5f8ea157cd37fb34327fbb4fc89dc66980336aa84c3 +size 3607994912 diff --git a/GRPO-Think-14B-8k.i1-IQ2_M.gguf b/GRPO-Think-14B-8k.i1-IQ2_M.gguf new file mode 100644 index 0000000..5eb892e --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db65ac25e921d766b79068660e16d10493eec29a8270032e0821d8f8018076d +size 5356147232 diff --git a/GRPO-Think-14B-8k.i1-IQ2_S.gguf b/GRPO-Think-14B-8k.i1-IQ2_S.gguf new file mode 100644 index 0000000..8c49420 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c5a7110172ea57ebd506468c1874bea0f5fbace6a1bf9d99eb8b2f26dbafd0 +size 5003727392 diff --git a/GRPO-Think-14B-8k.i1-IQ2_XS.gguf b/GRPO-Think-14B-8k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..54b16ca --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8551d9fec8f7b317a122cb1c74ba29b3c14d4fad5f02710e79ece27b14928fb3 +size 4704576032 diff --git a/GRPO-Think-14B-8k.i1-IQ2_XXS.gguf b/GRPO-Think-14B-8k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f4e901e --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0cca21dca052b39662b57a8bbf7e491bd73e7b6438dd2a43b3a3c11329d412 +size 4312834592 diff --git a/GRPO-Think-14B-8k.i1-IQ3_M.gguf b/GRPO-Think-14B-8k.i1-IQ3_M.gguf new file mode 100644 index 0000000..571a95d --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5535f42dc608bff751f0bd3b4312965a1963ff8358b1cd23c97237eaad32a686 +size 6916538912 diff --git a/GRPO-Think-14B-8k.i1-IQ3_S.gguf b/GRPO-Think-14B-8k.i1-IQ3_S.gguf new file mode 100644 index 0000000..aa75890 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d844ceeebaa1ba6f946fd76b33eadaa2a57c6adb4232aa0d3a50ea2e60769d +size 6693020192 diff --git a/GRPO-Think-14B-8k.i1-IQ3_XS.gguf b/GRPO-Think-14B-8k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4226c46 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b0da08b067b5459e7ef7e0f5c5d0bdcda2460d74285aa77e2d1558169f34c23 +size 6383362592 diff --git a/GRPO-Think-14B-8k.i1-IQ3_XXS.gguf b/GRPO-Think-14B-8k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9822540 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441221c65a1afbc607c8168fcccdc405670552eaad7141ea7fb1ef974abf4c94 +size 5946708512 diff --git a/GRPO-Think-14B-8k.i1-IQ4_NL.gguf b/GRPO-Think-14B-8k.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4e9effc --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b666bed1ae955bbf72872759ae734d4cf5203def9aa34211f532fff234c0823 +size 8549184032 diff --git a/GRPO-Think-14B-8k.i1-IQ4_XS.gguf b/GRPO-Think-14B-8k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f5cd9fe --- /dev/null +++ b/GRPO-Think-14B-8k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717c2c2b046f8a74b1cbcd1ae41212a894f40f32ecf681ee35e467365712d3b3 +size 8119841312 diff --git a/GRPO-Think-14B-8k.i1-Q2_K.gguf b/GRPO-Think-14B-8k.i1-Q2_K.gguf new file mode 100644 index 0000000..3a19f94 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df8e562173c1535dcf7f02a48de04a4a0a96fa5b8e76a35bf5b098d5cbb3459 +size 5770498592 diff --git a/GRPO-Think-14B-8k.i1-Q2_K_S.gguf b/GRPO-Think-14B-8k.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c3b7daf --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeadf075dc210d7e660dd9fc4e731e3af0f1706441b32a3b793527f1fc6f5055 +size 5397189152 diff --git a/GRPO-Think-14B-8k.i1-Q3_K_L.gguf b/GRPO-Think-14B-8k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..511b97d --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f1672386dc8073b22213b285de9da0ceb71bcd509fc40351329f37f804c628 +size 7924769312 diff --git a/GRPO-Think-14B-8k.i1-Q3_K_M.gguf b/GRPO-Think-14B-8k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5aec314 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e9e098aa9bb04dbc95608f2e725eb1c06dec12ec752857f36a19d48e568b99 +size 7339205152 diff --git a/GRPO-Think-14B-8k.i1-Q3_K_S.gguf b/GRPO-Think-14B-8k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a25ff60 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c492d7288d337e739a92772c652e8c276ad2ab1b6c137278449fc7626be0f5e5 +size 6659596832 diff --git a/GRPO-Think-14B-8k.i1-Q4_0.gguf b/GRPO-Think-14B-8k.i1-Q4_0.gguf new file mode 100644 index 0000000..a2aea98 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533cac1428085f87b0b2ae3ded6bf4d0770b58faae7eda2bf4d3cbd9f4bbca0c +size 8544268832 diff --git a/GRPO-Think-14B-8k.i1-Q4_1.gguf b/GRPO-Think-14B-8k.i1-Q4_1.gguf new file mode 100644 index 0000000..ad992d8 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7530090d3ed9756944c0c9ac22a23a27b2c5cb92f811f8b22fb2664e1c56324 +size 9392140832 diff --git a/GRPO-Think-14B-8k.i1-Q4_K_M.gguf b/GRPO-Think-14B-8k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..28277cd --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ad77d3ded422c2607b45d75added3bbdb5851ed99c66c1e82014cce9354c69 +size 8988111392 diff --git a/GRPO-Think-14B-8k.i1-Q4_K_S.gguf b/GRPO-Think-14B-8k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4832ce5 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf9734cb545384eb4186b6342d2361cc4c5b2a5041f0770b6a4409cdf782d0c0 +size 8573432352 diff --git a/GRPO-Think-14B-8k.i1-Q5_K_M.gguf b/GRPO-Think-14B-8k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7c22449 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6a82b018a907f137064a54f739fbb07737be124b6ef5fe2d1e9e48af60d6c6 +size 10508874272 diff --git a/GRPO-Think-14B-8k.i1-Q5_K_S.gguf b/GRPO-Think-14B-8k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d058ea9 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef154933ec22a5f6398e9bdf8ca3936dc1c342c4f4cb93bb0480bc75f0b32bfe +size 10266554912 diff --git a/GRPO-Think-14B-8k.i1-Q6_K.gguf b/GRPO-Think-14B-8k.i1-Q6_K.gguf new file mode 100644 index 0000000..31b5302 --- /dev/null +++ b/GRPO-Think-14B-8k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23765d96c59a9b60a724a615fa6bcf71f76b3bd9d694ea97e519bc5c2b4deeec +size 12124684832 diff --git a/GRPO-Think-14B-8k.imatrix.gguf b/GRPO-Think-14B-8k.imatrix.gguf new file mode 100644 index 0000000..fc1b405 --- /dev/null +++ b/GRPO-Think-14B-8k.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e5786db1738d003929efbf875315369da05ac17b36b0443e4a1c0f3f4e611b +size 8604128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c801677 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: Aletheia-Bench/GRPO-Think-14B-8k +datasets: +- Aletheia-Bench/Aletheia-Train +language: +- en +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Aletheia-Bench/GRPO-Think-14B-8k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRPO-Think-14B-8k-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GRPO-Think-14B-8k-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/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-Think-14B-8k-i1-GGUF/resolve/main/GRPO-Think-14B-8k.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. + +