commit 84e09680178a3ef6af84e9b2ea51c40bc33a3424 Author: ModelHub XC Date: Sat May 23 21:00:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..afae050 --- /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 +MT-Gen1-gemma-3-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen1-gemma-3-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-Gen1-gemma-3-12B.i1-IQ1_M.gguf b/MT-Gen1-gemma-3-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..33c8eb1 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88bc868b266bdfb9ac0c6e276123815baf41613d833f4811c46e10ad947f8a7 +size 3164729856 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ1_S.gguf b/MT-Gen1-gemma-3-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..6f93629 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e16b13a18751382cb85309d28d494584ca32317a96bd6587a40708f4d30897bd +size 2947416576 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ2_M.gguf b/MT-Gen1-gemma-3-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..c334e88 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07030ff06e9e70edf49e3f675af7c059deea2929bb5bacbb8ca3da7b60c881b9 +size 4310462976 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ2_S.gguf b/MT-Gen1-gemma-3-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..82e0d2d --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f47f19de19e488b3cc44e282697598ce4ebf1d0709b03a2cb69777f9668656e +size 4020711936 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ2_XS.gguf b/MT-Gen1-gemma-3-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b44fcdb --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbb49bf741aa6e192cf3fbaa10aaf5bc07943cf525b52ff01f1e71650c590a9 +size 3840262656 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ2_XXS.gguf b/MT-Gen1-gemma-3-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..143a0c2 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d50c4f446addd4dabb46ee33dddde6fcf0a48e83b2eb79292c63e3800f2f4d +size 3526918656 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ3_M.gguf b/MT-Gen1-gemma-3-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..af48aea --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d1d51026d130dd5cc0af4135d3c5be5aeeb15391916382f1f4e232841763b4 +size 5655724416 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ3_S.gguf b/MT-Gen1-gemma-3-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..9d5519e --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1414ca817ebe34bcebb53742b6c2cceb8a7adb7a284058ba0fc7b4a1ac59f0ba +size 5458317696 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ3_XS.gguf b/MT-Gen1-gemma-3-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7277a3a --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04faad37856d55e66432ad0efec02eb837f7186d67e388adc407d9ee67eacfae +size 5206167936 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ3_XXS.gguf b/MT-Gen1-gemma-3-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a13c3ba --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0ac7223c5b1f72488d7356edc597a9e8ec4c4e67364bba2ddf6eeafed76c94 +size 4784902656 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ4_NL.gguf b/MT-Gen1-gemma-3-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..92bd1c6 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a7a55e4376fa8ac798a4107d5942a806ee290a27f96f24c43e9f4df8ec9385 +size 6887166336 diff --git a/MT-Gen1-gemma-3-12B.i1-IQ4_XS.gguf b/MT-Gen1-gemma-3-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fe2d98d --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ce5173d6eb16ccde8b20dda13522bd4a528ef80fdc9e7dde4867ce31ea0f98 +size 6550966656 diff --git a/MT-Gen1-gemma-3-12B.i1-Q2_K.gguf b/MT-Gen1-gemma-3-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..66e493f --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109f145cacd12cced4ffa8db17b10aac2573a8fb0b25c7a08beaf1f587d269a7 +size 4768223616 diff --git a/MT-Gen1-gemma-3-12B.i1-Q2_K_S.gguf b/MT-Gen1-gemma-3-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6717df9 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd41314bd95b9caa9b8ea4b96cd592b38a7df44fee8b30b61e38758cdcb0cc3 +size 4448612736 diff --git a/MT-Gen1-gemma-3-12B.i1-Q3_K_L.gguf b/MT-Gen1-gemma-3-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bd597e8 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187303332e37be20637f86212960ee26deb906b1c4260997c4e871b32f61a850 +size 6480187776 diff --git a/MT-Gen1-gemma-3-12B.i1-Q3_K_M.gguf b/MT-Gen1-gemma-3-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..01fd6e7 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfdc6e9f4cebbb90037c6155e705b994bb5e9fff18a1d9bbdd216f5ce30b569d +size 6008820096 diff --git a/MT-Gen1-gemma-3-12B.i1-Q3_K_S.gguf b/MT-Gen1-gemma-3-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9f8b79a --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65479774faff2996fc849581a68b8a6aebd90124af011ea913c72c346b1f47ff +size 5458317696 diff --git a/MT-Gen1-gemma-3-12B.i1-Q4_0.gguf b/MT-Gen1-gemma-3-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..f651217 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d744094870c98e309b309bfea45a8f812327aed4e4aff87f2531836618ae09d +size 6909284736 diff --git a/MT-Gen1-gemma-3-12B.i1-Q4_1.gguf b/MT-Gen1-gemma-3-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..8bb7dc3 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2619164716032acf449135f7e90dfd9bc8a7d712b21e4400626c4862c8a1e9de +size 7559565696 diff --git a/MT-Gen1-gemma-3-12B.i1-Q4_K_M.gguf b/MT-Gen1-gemma-3-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..1a080ba --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d6f4a06f3077b66105c00abe36c8a2ae0fe65d641bf8445aa2750f2842cf63 +size 7300780416 diff --git a/MT-Gen1-gemma-3-12B.i1-Q4_K_S.gguf b/MT-Gen1-gemma-3-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..950f7d3 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9893e9d968da0831eb35bd3bcb62d16db5637b2495cd6bc619773cc6d89e629 +size 6935335296 diff --git a/MT-Gen1-gemma-3-12B.i1-Q5_K_M.gguf b/MT-Gen1-gemma-3-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..73d32b9 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9237e7a1a3b10640061ed7b2419d0ffdb2efb1914e0f673f7bd325b1e54e4aa7 +size 8445038976 diff --git a/MT-Gen1-gemma-3-12B.i1-Q5_K_S.gguf b/MT-Gen1-gemma-3-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..99cb155 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa20129398ec72e5b57136b87bc243585c9bba459e90f9e770795fbe8272a8a +size 8231965056 diff --git a/MT-Gen1-gemma-3-12B.i1-Q6_K.gguf b/MT-Gen1-gemma-3-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..a554219 --- /dev/null +++ b/MT-Gen1-gemma-3-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79913c0079fee3f155927d312e3269e0ee78a30822f9f41aa30fb661561ee0ea +size 9660813696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce8a1b3 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: zelk12/MT-Gen1-gemma-3-12B +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/zelk12/MT-Gen1-gemma-3-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT-Gen1-gemma-3-12B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-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/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen1-gemma-3-12B-i1-GGUF/resolve/main/MT-Gen1-gemma-3-12B.i1-Q6_K.gguf) | i1-Q6_K | 9.8 | 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..e3e7e7d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22bea36f6feb93437da5fabd6041290331bb35cefd213fec05692d4bfec229a6 +size 7433101