commit ca3709bf9b0642bc34cbc753eab661b0099d3935 Author: ModelHub XC Date: Thu May 14 23:26:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ca0a279 --- /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 +Newstar-Qwen3-0.6B-KTO.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Newstar-Qwen3-0.6B-KTO.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ1_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ1_M.gguf new file mode 100644 index 0000000..27c1c87 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f262c79654517edcba5be9346dcb82ce8d6330010c19ee8fbf5d2735fdca49a +size 216048544 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ1_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ1_S.gguf new file mode 100644 index 0000000..50f209e --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147ef76d7564e020850a0bc1b22315faf2f37d1cfe3a76e39b3935f4353486e1 +size 208012192 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ2_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_M.gguf new file mode 100644 index 0000000..a93d604 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e115f6bd49046aca7d08d6378c8905df03006c34055224e6b5ea440f316f71d +size 264905632 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ2_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_S.gguf new file mode 100644 index 0000000..3a99846 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ff773af6ce847878f055b0a2f09844b58034a343cabeb5738824f8897ddaea +size 254190496 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XS.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b0ca232 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e998766d3c42e72455f814f391a20ef8a8442c80af8381614033474d2b661e0 +size 241992608 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XXS.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d17ecdd --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22043130829861bd6d3712e9332949330c9c040781ccd978decbe5471f79cf8 +size 229442464 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ3_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_M.gguf new file mode 100644 index 0000000..46aec1e --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7f5848f02cd30605ed7ea400756c321a7f7648cde8812989bf671c06383105 +size 336023456 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ3_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_S.gguf new file mode 100644 index 0000000..c371d4f --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de2897b6bbc1a895a37386c982a526b16333e48cc7c472912860c0c4b654f7c +size 323071904 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XS.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c0f102b --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b0651837b2c94b62bb0fc2df9b774b6f9d43a704cd96e912a4c49a604b28d4 +size 312749984 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XXS.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..58ab666 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb876dc1896eed0c14ea57688e732d0b87bd8f297938632a21512a1991b5eeee +size 279012256 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ4_NL.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ4_NL.gguf new file mode 100644 index 0000000..3aef5ef --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bb0663d774c0b0eb631f5339290f99cc47f9fca5d55742e465880bbd972bd2 +size 381562784 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-IQ4_XS.gguf b/Newstar-Qwen3-0.6B-KTO.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9b479f1 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084bc969644fd282e4363b1b1b087d914758dc43de8008806ff17be49b2726d0 +size 367800224 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q2_K.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q2_K.gguf new file mode 100644 index 0000000..4855f6e --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d326e973b7dd9f2d88cfa8077a4aaffb53f34a154a1464ec9e2401f6f6f45284 +size 296234912 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q2_K_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q2_K_S.gguf new file mode 100644 index 0000000..15420db --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6970d4a1403f0229d1bf3620297fbc2aeea00b83013dc375d82a977147578581 +size 280555424 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_L.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_L.gguf new file mode 100644 index 0000000..93e6af8 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7fc6ca7cfa7a70674352733285dca33491707f92b9c5574cffea7da5aab8a5 +size 368488352 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_M.gguf new file mode 100644 index 0000000..db3c825 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f90e509820c174d6fce47d0f339d8069e12cbae14d5a0348b9aa15043965cc +size 347123616 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9b098d9 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14a1c9d51166b07989881f97f025f9e3c9662d508c7cc1e4ed679ecdb64528a +size 323071904 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q4_0.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q4_0.gguf new file mode 100644 index 0000000..8fda2ab --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9acc7d2825c5a346df626130c6e8cb6e7152c5d32cb02864f6baea33b910b935 +size 382152608 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q4_1.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q4_1.gguf new file mode 100644 index 0000000..9b955b7 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ab0bcd6a42ca96ad69607c2c4fb7907123a2b5ec5b0b5acfb4ba05a22f5602 +size 409087904 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5ce495c --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c652b7f524cc3ab0839d066e0b772556460103e09a20ff2b33943b680675f9e +size 396701600 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_S.gguf new file mode 100644 index 0000000..393cffd --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1d27aeed7bef60c7cea42c0ee610d955576404daa920b5f5d4eede79a4298f +size 383266720 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_M.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f8813ef --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea32485d5b6b3b43cc514428d34a84fe56c04fe3933719a59147875eb0442b6d +size 444411808 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_S.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_S.gguf new file mode 100644 index 0000000..61423ad --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1516715397ab1a90db8f6ac2c2cacd6ceb6c9255a0206eb16131af22cd8cac64 +size 436613024 diff --git a/Newstar-Qwen3-0.6B-KTO.i1-Q6_K.gguf b/Newstar-Qwen3-0.6B-KTO.i1-Q6_K.gguf new file mode 100644 index 0000000..1d5a8e1 --- /dev/null +++ b/Newstar-Qwen3-0.6B-KTO.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f230f0a4770758e3ab4488e9199b42a0facc937b2b0a9390ff373d213d8aff86 +size 495103904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eaae6a2 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: NewstaR/Newstar-Qwen3-0.6B-KTO +datasets: +- trl-lib/kto-mix-14k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/NewstaR/Newstar-Qwen3-0.6B-KTO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Newstar-Qwen3-0.6B-KTO-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-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/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Newstar-Qwen3-0.6B-KTO-i1-GGUF/resolve/main/Newstar-Qwen3-0.6B-KTO.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..ac5bb2c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965d31bd6d62e50d6d6f737d0cc37d6ffc88799ac3b4272a6f260cbc053db121 +size 1153369