commit 751d0f55c145cb39e885128022239f1911009c88 Author: ModelHub XC Date: Mon Jul 20 09:55:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..01cab6f --- /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 +Qwen3-14B-ARPO-DeepSearch.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-ARPO-DeepSearch.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_M.gguf new file mode 100644 index 0000000..a8a889c --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534e7ec2b32cb4c34071d72103b03bf76ae24f948ef5b254f99c3aefcb24ab33 +size 3849656448 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_S.gguf new file mode 100644 index 0000000..2698f52 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad150fc366db6f1454b04fafdbbcb961d93910389b7689413b7dfef03941adbf +size 3579934848 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_M.gguf new file mode 100644 index 0000000..cb775e9 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80dd0856980409a79007f117e23806fa3b96f927cb579b8d80e04409ad3aca5 +size 5322941568 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_S.gguf new file mode 100644 index 0000000..1917ede --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a60a8c957cf677b33d63f328bd9075025755766f87b33941c0672eed9111454 +size 4963312768 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XS.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5f9e017 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10aa66b4e870adbd97d494dc38643f58d5ad99af0055345358296daf35f8ffa8 +size 4691589248 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XXS.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7c096ed --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe9575ba7799c5bc7e74e8ddb920b1bd49a9f5627979c3bd3d0b042a585832b +size 4299192448 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_M.gguf new file mode 100644 index 0000000..117291a --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7432953a141615e5a506a213289005475c298c2b7477367f4ac0ed8a9a9f0535 +size 6883410048 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_S.gguf new file mode 100644 index 0000000..c79c7ea --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc03e58f32c84aeac40c78c02e7bf45c58abbdff3fd853f3ae40ab1d0a7cc02d +size 6684958848 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XS.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XS.gguf new file mode 100644 index 0000000..cbe5f4d --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73112a3375fa2f63f454d80534bc14fbd78239ab8e3db6eb64f61651ff463ad +size 6375301248 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XXS.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..04504cc --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2656a2f82072d4c528d6a63db60c3f454f2701080158c25a6e6fcfba6ddd1d1 +size 5942666368 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_NL.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_NL.gguf new file mode 100644 index 0000000..f275fa7 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf35853a011d7c352063c4b7e7dad51a90c8147fb8aafc34f177e3c821d7acff +size 8541363328 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_XS.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5dadeee --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d32486bd64bb71af13be959bb5730df8c8fb9833bd95ca5a6783f9112567b7f +size 8110730368 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K.gguf new file mode 100644 index 0000000..32da529 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085c9762ed990770e85dc6b4d22879cdcb36264aa2ca464f760ec718b846b0ed +size 5753984128 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K_S.gguf new file mode 100644 index 0000000..03459c6 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a80b54237a6a8896864451ff612e740b1b419fe19d03b0151eee7454e3dfe0 +size 5389849728 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_L.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_L.gguf new file mode 100644 index 0000000..6a5cfab --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46767c252833c1a919b8852f8bd4f8ea00b63f3e6ec15d89b4cf7759d1ac1585 +size 7900651648 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_M.gguf new file mode 100644 index 0000000..18328fb --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d3631eff4fc3c37b35f75b116047b7f007aa31470f6005980e0d3eefbe0584 +size 7321313408 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_S.gguf new file mode 100644 index 0000000..05c6fac --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e091e1ecf0b2fc4f8a04359a9b64546951f21a5220e67d124fec9d936f3601 +size 6657106048 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q4_0.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_0.gguf new file mode 100644 index 0000000..475b30d --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b690c34cff5e36b01f5c2763bfaf7ff199e9c6b5d2afcb4c221d100d7493a486 +size 8543001728 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q4_1.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_1.gguf new file mode 100644 index 0000000..d67d456 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b7067570f330fab582f1e1b6e4a335ebabb515575f6f6a8e735af14c350b71 +size 9389522048 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_M.gguf new file mode 100644 index 0000000..69a0b14 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd39399d8d397e95195e88d6851078336f71e22f7f7df3bb15f67822b63e073 +size 9001753728 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2884267 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bac8331b8f2e73551e8fa89c595c2224f6135a54e967254ad216ac392200171 +size 8573475968 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_M.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_M.gguf new file mode 100644 index 0000000..96d2990 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bc687242ae1c3d520c1f0155437960863b3dd9b5faf0c26f8d3de30fb93e47 +size 10514570368 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_S.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e856a5e --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b34b59f3159174a4ce18c2b5780655e731dca73e53cc184df36741e46b6b06 +size 10263895168 diff --git a/Qwen3-14B-ARPO-DeepSearch.i1-Q6_K.gguf b/Qwen3-14B-ARPO-DeepSearch.i1-Q6_K.gguf new file mode 100644 index 0000000..5a063be --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea0770978a656361c4c036a605fd5acb102e7038cee75fbf45b8772dc09b6c17 +size 12121938048 diff --git a/Qwen3-14B-ARPO-DeepSearch.imatrix.gguf b/Qwen3-14B-ARPO-DeepSearch.imatrix.gguf new file mode 100644 index 0000000..be1f036 --- /dev/null +++ b/Qwen3-14B-ARPO-DeepSearch.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b805d9200c5a414831e62d4405549984c04e98f7c830e8f183d6e3be97a002fe +size 7743552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b043a8 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: dongguanting/Qwen3-14B-ARPO-DeepSearch +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- agent +- tool-use +- reinforcement-learning +- qwen +- llm +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/dongguanting/Qwen3-14B-ARPO-DeepSearch + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-14B-ARPO-DeepSearch-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-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/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF/resolve/main/Qwen3-14B-ARPO-DeepSearch.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. + +