commit 6f5533d7bcb10443a36b9a1b0e2d99ab0d2ea025 Author: ModelHub XC Date: Fri Aug 7 14:01:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e34c2bd --- /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 +L3.1-12B-Niitama-v1.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-12B-Niitama-v1.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ1_M.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..3482c47 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879a3b5c7b78f5ae74ca46d127e4d8554ee6c122d3a82480ac089fb8cbd29eb0 +size 2972273024 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ1_S.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..dbb696a --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ea5a679b3b2790530ad4efaf3a0b2e0fe0aaea409e3abfe5e5d2960e86b438 +size 2758756736 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ2_M.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..6d83e59 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc24aa83b486d68cbfab85e548f5b07c06372506c2377c9f355c5e74b09f4cb6 +size 4125059456 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ2_S.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..d29fba4 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6911f899a44d838f0ba0c970aefbafc7ef778cb6c5045812d6e80e2bd88afb0 +size 3840371072 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ2_XS.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f652543 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdb9068ec775fc9754d12c34919b62ed07c502224c9d70eb017ba6f45058095 +size 3637987712 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ2_XXS.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e957f3c --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9248aa0bffe3d71ed8bf15257d2a161d2607c7703ab0ad51d2a1a12d64ba5b +size 3328133504 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ3_M.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..f44cf48 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d5ea62769eb7c40e04275a68674778ad81eb289779f9cb63b10b0cd098ead7 +size 5344987520 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ3_S.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..8c2b01d --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b178d76568234146e5900848934e784d5686f24ed51e11ed028a90a5b9834f27 +size 5191240064 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ3_XS.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2ccda15 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163daf9412a82626e6dfd10ae5a2d036c16e5bc7e0089ba12b1ba886cb9dfb5c +size 4945873280 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ3_XXS.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..eec3f77 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91cbc321d34564d2f55b3e85e8725bd11abbea123c0a879b8e869188101b5674 +size 4615006592 diff --git a/L3.1-12B-Niitama-v1.1.i1-IQ4_XS.gguf b/L3.1-12B-Niitama-v1.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..46546ac --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87942820f78a66ef045f07d7da1267ad7bc16ed22d0ccd1619920069b0fd8a6a +size 6312569216 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q2_K.gguf b/L3.1-12B-Niitama-v1.1.i1-Q2_K.gguf new file mode 100644 index 0000000..e47fc23 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4654a55df2911febe158e82c8828e99158e924d2ebc8adcee3e70971da0c5f7 +size 4463126912 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q3_K_L.gguf b/L3.1-12B-Niitama-v1.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3346aa1 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f26c21f365140ffba662c61751892774ea5e7f8659c9310bd2f9b332c14761 +size 6150687104 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q3_K_M.gguf b/L3.1-12B-Niitama-v1.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4c0fa71 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9fb86f59bf31878923b5ef54b9c0bc9d9da74d7207c075f99d70c46b01c9cf +size 5695605120 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q3_K_S.gguf b/L3.1-12B-Niitama-v1.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8def077 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397ae3f49031dd61c85c240e2f4ac86be8dd58229828f25b11b9a8dade9ca32a +size 5164501376 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_0.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_0.gguf new file mode 100644 index 0000000..7984a27 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c23e18f688160418ac68d5b8e7b77aaa2bddda069c80c2ddd8290d39b1e927 +size 6646704512 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_4.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..a9d4807 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0daa3353c067a7674d043fd6f9c0f0f0d1546e50509b9449702c8abaa23e0f8 +size 6624684416 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_8.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..afa30e8 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062c932016417447d2feda66f175c6f0bc3388ce71b5bfb4f581cce4a3a5a695 +size 6624684416 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_0_8_8.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..0713fa4 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc31c6ab9e06e1220277bc77449ba8bc7f198ee2a6bb3a24859531932cd6783c +size 6624684416 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_K_M.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a03355b --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4e53002e6b3a5d5c8475d85c59782e42d62a6aaa61153c5f68575ba0d30975 +size 7013968256 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q4_K_S.gguf b/L3.1-12B-Niitama-v1.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bcce09a --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c45754282ac15212e2dda2b858eafb5b1bff6537a2a3f68834d162bc121436d +size 6670821760 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q5_K_M.gguf b/L3.1-12B-Niitama-v1.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c1be842 --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1ae30ce37f7cd4ff581d4ee5b2f7d71ff6122cf279bb96431804351ef7f2a1 +size 8199514496 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q5_K_S.gguf b/L3.1-12B-Niitama-v1.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3bf9b0e --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754f18470d9ef311308909f15dd186fe11792063c03e56315f142a6c827da29d +size 7998974336 diff --git a/L3.1-12B-Niitama-v1.1.i1-Q6_K.gguf b/L3.1-12B-Niitama-v1.1.i1-Q6_K.gguf new file mode 100644 index 0000000..0283a4c --- /dev/null +++ b/L3.1-12B-Niitama-v1.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e94f0af6abcde02c43fc9a912de528bf46925cf3c9cd939163f3a570d8669c +size 9459157376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..74f3ecb --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Darkknight535/L3.1-12B-Niitama-v1.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Darkknight535/L3.1-12B-Niitama-v1.1 + + +static quants are available at https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-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/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 3.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 4.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 5.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.7 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.7 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 6.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-12B-Niitama-v1.1-i1-GGUF/resolve/main/L3.1-12B-Niitama-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 9.6 | 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..38867c1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2240c22f78d399a1809d41a644a7bbf9e9df9db199a5b6c03145ea03805ee88 +size 7482253