commit ec05a06880ec6fa82e7cdaaece542f208456ea74 Author: ModelHub XC Date: Mon Sep 28 09:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-LLM-AR-V2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8ca7bee --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Marco-LLM-AR-V2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Marco-LLM-AR-V2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-LLM-AR-V2.i1-IQ1_M.gguf b/Marco-LLM-AR-V2.i1-IQ1_M.gguf new file mode 100644 index 0000000..b28e55e --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6af7e2781e0d077f3c51e8272639f03ac38fa254a16b85525f2e11323670b78 +size 2042196640 diff --git a/Marco-LLM-AR-V2.i1-IQ1_S.gguf b/Marco-LLM-AR-V2.i1-IQ1_S.gguf new file mode 100644 index 0000000..aa560bc --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477a12d101c6495002abaa9af264844e1adfb481060495cee1bc7272b007f103 +size 1903667872 diff --git a/Marco-LLM-AR-V2.i1-IQ2_M.gguf b/Marco-LLM-AR-V2.i1-IQ2_M.gguf new file mode 100644 index 0000000..db89302 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2551bf7acf1458037280c2dcf7e230e321a502d4854a57c4a45633d44237c55b +size 2780342944 diff --git a/Marco-LLM-AR-V2.i1-IQ2_S.gguf b/Marco-LLM-AR-V2.i1-IQ2_S.gguf new file mode 100644 index 0000000..d915a3c --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2927d2e557a54124e2ec58f5d5048650991977ea6028c8348066ad405052d8cb +size 2595637920 diff --git a/Marco-LLM-AR-V2.i1-IQ2_XS.gguf b/Marco-LLM-AR-V2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..aeff620 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523f8c881c33af9600a1ee45b84d99568c89160f2810dccc5940fb8cb048ab62 +size 2469022368 diff --git a/Marco-LLM-AR-V2.i1-IQ2_XXS.gguf b/Marco-LLM-AR-V2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..71ecf14 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a082f8eb9c67e8e207b55a05b5e5e28df27244cc8f595c6d98bda953b410fc32 +size 2273077920 diff --git a/Marco-LLM-AR-V2.i1-IQ3_M.gguf b/Marco-LLM-AR-V2.i1-IQ3_M.gguf new file mode 100644 index 0000000..f287d60 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328f364564c918f6c317ab792363ab3e4ed0b80c062167a5a4b68346fb153cb2 +size 3574012576 diff --git a/Marco-LLM-AR-V2.i1-IQ3_S.gguf b/Marco-LLM-AR-V2.i1-IQ3_S.gguf new file mode 100644 index 0000000..37877ad --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d01d67cd24419ca44912d7d9a427ffae4a8b29dfcff6fa08bff048d846456e +size 3499192992 diff --git a/Marco-LLM-AR-V2.i1-IQ3_XS.gguf b/Marco-LLM-AR-V2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..99a8934 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04298656153feee533890676bf6aac5c0787d54aba73c23796a4c0930e365017 +size 3346256544 diff --git a/Marco-LLM-AR-V2.i1-IQ3_XXS.gguf b/Marco-LLM-AR-V2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..377b5c5 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd84b9a2e2f85f2c3638b69de024f478d40951559933ab22f74345ff32c888da +size 3114515104 diff --git a/Marco-LLM-AR-V2.i1-IQ4_NL.gguf b/Marco-LLM-AR-V2.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0d3d8a0 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827f75bd6a5c2bfce023cc525c9de7328426928b1a82fe320baba46b63873be3 +size 4437813920 diff --git a/Marco-LLM-AR-V2.i1-IQ4_XS.gguf b/Marco-LLM-AR-V2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0362e46 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e470835792bf9be8f649185083e1404cf39a4a924962ee74ae67d29ed0456c5f +size 4218473120 diff --git a/Marco-LLM-AR-V2.i1-Q2_K.gguf b/Marco-LLM-AR-V2.i1-Q2_K.gguf new file mode 100644 index 0000000..07d8712 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8f21489daec1bd2397947e6313f5eb3d0135eb819fffefd6da060a202a84a1 +size 3015940768 diff --git a/Marco-LLM-AR-V2.i1-Q2_K_S.gguf b/Marco-LLM-AR-V2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e3a198c --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ac5de6464a72123139f700b5c843548ee6bee20263df2bd846cf3400788e3d +size 2834074272 diff --git a/Marco-LLM-AR-V2.i1-Q3_K_L.gguf b/Marco-LLM-AR-V2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4d554e4 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5412066c010b58e75967701212cfc7081cf7fd1ed703bdb7cd02510bdb4c8a1d +size 4088459936 diff --git a/Marco-LLM-AR-V2.i1-Q3_K_M.gguf b/Marco-LLM-AR-V2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4550c4a --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f76883441cd87d0118c6047ba2c520985f97f7f1e20e60ffbd754d09f3c1ae6 +size 3808391840 diff --git a/Marco-LLM-AR-V2.i1-Q3_K_S.gguf b/Marco-LLM-AR-V2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..604e3c6 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58da170755fa667487b1f051ff3add5cbc35f6b006a85cbd4d5807cd0c1837e9 +size 3492369056 diff --git a/Marco-LLM-AR-V2.i1-Q4_0.gguf b/Marco-LLM-AR-V2.i1-Q4_0.gguf new file mode 100644 index 0000000..7041bb4 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1d3d42b2cedfcb858f757ea9977a91a7bb08cc2d6217b0b7b1ca9f6267372c +size 4444121760 diff --git a/Marco-LLM-AR-V2.i1-Q4_1.gguf b/Marco-LLM-AR-V2.i1-Q4_1.gguf new file mode 100644 index 0000000..7384f6d --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49680a59af74efdec2b962f331e4ad219da4c087d82af9261298601297d018a +size 4873284256 diff --git a/Marco-LLM-AR-V2.i1-Q4_K_M.gguf b/Marco-LLM-AR-V2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..949d046 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7b1e1b6fbb54c004c1fc2c1be7bc23336447497efc8046be2e2b949d42d01a +size 4683074208 diff --git a/Marco-LLM-AR-V2.i1-Q4_K_S.gguf b/Marco-LLM-AR-V2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b783cfe --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73208c125ecfdf1887d07978183e48536f0c8ed3d9fe359940cfe9898b42a6a4 +size 4457769632 diff --git a/Marco-LLM-AR-V2.i1-Q5_K_M.gguf b/Marco-LLM-AR-V2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ecb33d6 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250aeafb3633035708670f56626f0538eb58dfe8f47bad871cb5166cfdfc8eb2 +size 5444831904 diff --git a/Marco-LLM-AR-V2.i1-Q5_K_S.gguf b/Marco-LLM-AR-V2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..bbad050 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98f9c075d2c40f96dc3b2f8de38608387081b3d6216795f194a15efe855feb6 +size 5315177120 diff --git a/Marco-LLM-AR-V2.i1-Q6_K.gguf b/Marco-LLM-AR-V2.i1-Q6_K.gguf new file mode 100644 index 0000000..0e287d3 --- /dev/null +++ b/Marco-LLM-AR-V2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3234c5f925ce98a4a065069fd1753446b06b3c9a57f2652fd14317c8a309f349 +size 6254199456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..998bbd4 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: ATH-MaaS/Marco-LLM-AR-V2 +language: +- ar +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- pretrained +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ATH-MaaS/Marco-LLM-AR-V2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-LLM-AR-V2-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Marco-LLM-AR-V2-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/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-LLM-AR-V2-i1-GGUF/resolve/main/Marco-LLM-AR-V2.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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. + +