commit d325a5a000697cddd8fccffb861bcb2f3bdb5832 Author: ModelHub XC Date: Sat Jun 13 18:16:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..408cd8a --- /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 +MultimodalTopic-12B-Gemma3-Flash.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_M.gguf new file mode 100644 index 0000000..04483fe --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c73c6859266f6188e24a658c07b086e163f97c7479047637df15f9385520982 +size 3165894656 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_S.gguf new file mode 100644 index 0000000..f0a1635 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e10d6b858fbfcfdcb69f076576e4d515e4b39dcf0a2ef0f0bb3bdd3ee2edd602 +size 2948581376 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_M.gguf new file mode 100644 index 0000000..eb7658e --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13629bd805f7892d56eeab0e848d68273f441062b9827cd64574a4dcd0a129a7 +size 4311627776 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_S.gguf new file mode 100644 index 0000000..9cf13f0 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4234e86e9e25e589fbd93f8bfee4a7932b4bc4dae4af2d9e40f02db3f8c5e2 +size 4021876736 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XS.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XS.gguf new file mode 100644 index 0000000..20eae0a --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ea51781d59398089de10c95134b64c0e817b6fceaa03985639e32fe1b8610d +size 3841427456 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XXS.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..25eacda --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ba789bafa7daded63056d6f43da591b9bdc7cfcce2d4b612d60c1fec607ebd +size 3528083456 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_M.gguf new file mode 100644 index 0000000..61e8e95 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56c04ea4f52aa9c1900c46771476aad060faecc592442b347d419cd9972d16d +size 5657112096 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_S.gguf new file mode 100644 index 0000000..22d9088 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef347c7bf77edfa72ad995d66ed943de29932d918c93235e088ecb409261b15 +size 5459705376 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XS.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2689de6 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9b28c082eeadbc672c9580f897fe8bf4133de0facfc4a76396dc3f46dba0fd +size 5207555616 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XXS.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d42dc56 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69879f82b8edda36ddcf9467871b70898c163b1687f78c46c5e24724c44afb5f +size 4786067456 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_NL.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_NL.gguf new file mode 100644 index 0000000..254b36c --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527945981b342e73e03809c79ecdc5e8074daa2631fb1f4f54c70a8199ac50bf +size 6888554016 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_XS.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e0c21f9 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ad2eaa25664045ad500485ff0804c91b3ed4125e808c15e423dcb44ac50daf +size 6552354336 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K.gguf new file mode 100644 index 0000000..7842b13 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b3af3a048319cbf263b099545d20d707ae94c2bd85d77cec662718abc76df1 +size 4769611296 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K_S.gguf new file mode 100644 index 0000000..5cb301a --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076ba7842f1ead23b7a52892ed4bf59ab1b020292af43b0bc2342ab712dbd140 +size 4450000416 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_L.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8429442 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0023d49faf199853b2bf2bd10972333531d15391df94a3bdf043d7ec499ca602 +size 6481575456 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_M.gguf new file mode 100644 index 0000000..317bf45 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214fec1ad2dd6f95944cb2be398d5e7d1866e1a1ad21b24ac7d6c2040c1ff31b +size 6010207776 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c18d709 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bdb1000512d02e4b45819c2810540051572c8047af3b98773ce0088a469a457 +size 5459705376 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_0.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_0.gguf new file mode 100644 index 0000000..8d1343c --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43d81be5a742063c0fcf1b9522e984fd576b413fca530fad08c819a85dd3f44 +size 6910672416 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_1.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_1.gguf new file mode 100644 index 0000000..39ef666 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc6cfe9dc3560e44f70886694d5f60e3e3771d8b3ab39eb6bd6b7b83ed43f7b +size 7560953376 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_M.gguf new file mode 100644 index 0000000..798312f --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd803c372a90e7310f717054798582a310b74d2e0b568d99b9694f2cd3919dcb +size 7302168096 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8ecd28d --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a55027c2788c603c7727d7fdba4de35ddaf367cf10ff16d0541c2f42f3f533 +size 6936722976 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_M.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6cc74e3 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0530a9634447dfa3055257ec45daeaeed60f1e2b5065fce7e6548532e8c1b755 +size 8446426656 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_S.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_S.gguf new file mode 100644 index 0000000..cd576c2 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfaf9c6a71fa1415cf5c333a6ae0e495ee94ab147d27d805b84fba65880d6ef7 +size 8233352736 diff --git a/MultimodalTopic-12B-Gemma3-Flash.i1-Q6_K.gguf b/MultimodalTopic-12B-Gemma3-Flash.i1-Q6_K.gguf new file mode 100644 index 0000000..e5c9808 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:063cc3b80fea0156ba99ff046998d5331f9e4814346c7017a11fb4c2e325809e +size 9662201376 diff --git a/MultimodalTopic-12B-Gemma3-Flash.imatrix.gguf b/MultimodalTopic-12B-Gemma3-Flash.imatrix.gguf new file mode 100644 index 0000000..a0d3947 --- /dev/null +++ b/MultimodalTopic-12B-Gemma3-Flash.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46260a54f68ffd481a3f3fba0b05c331027f3fce1ffe06697b2fec160f43e1f4 +size 7473632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e8942b --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: SF-Foundation/MultimodalTopic-12B-Gemma3-Flash +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/SF-Foundation/MultimodalTopic-12B-Gemma3-Flash + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MultimodalTopic-12B-Gemma3-Flash-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-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/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_S.gguf) | i1-IQ2_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ2_M.gguf) | i1-IQ2_M | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_S.gguf) | i1-IQ3_S | 5.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_0.gguf) | i1-Q4_0 | 7.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q4_1.gguf) | i1-Q4_1 | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/MultimodalTopic-12B-Gemma3-Flash-i1-GGUF/resolve/main/MultimodalTopic-12B-Gemma3-Flash.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. + +