commit d01684022a7072dfec13ed6254bbb8bee47095f6 Author: ModelHub XC Date: Thu Jun 4 20:29:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dbcedad --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.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 +Mistral-NeMo-Minitron-8B-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..eb3e9cc --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453b2d8f5bc7f7ddf2ad2df3aa4f06ade7699330ec7fa6b5545366c0f872fdd7 +size 2269800704 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..b46de39 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7102dbff21d6018203e0d13b723e07cc844763e042d0da251bee30d55225486 +size 2122959104 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..58dad21 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64270b5b98ee43a7232166d2f431242ca8eb006eb8f9cc34cca40a48601cc47 +size 3099946048 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..f0a3be3 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0383ee4e2eb4bf7751b73abaefc13835291275a36e09d302f305f8b3eab4af +size 2904157248 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XS.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5735a38 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a0cd2c1305e9725ff4c8fc17af5239da9b4e8f743f85541937969629b91c68 +size 2731297024 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XXS.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5a7fb03 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb336f7f478df70e504eff4bac7a27ff41ba4912542da1984327e5721c18e12 +size 2514536704 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..f8f5e76 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317d5a6e87c234b46c265d9c7316d128c9cd36be1822f2d77f0f8475cd65ffab +size 3976974464 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..5cab144 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce1f5ffe8a0976bbab37af893dbd60fcc40f07493f8d3d093a21d5761ce1cc1 +size 3856511104 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XS.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..280f2be --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4631a851718f5a4a6ff61495d57777c15057c8659a9eecee36b5a98e6d656590 +size 3684479104 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XXS.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..feb71b7 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c8911d3f4d1cbcb47b9281742e36d1a45d2158bdf206cc277fa2858cc7a442 +size 3428035648 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-IQ4_XS.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..01b8229 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f5f779727ce515e073242664872aaabd89350562ba0530b3bfdb91b0f13f47 +size 4660442048 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q2_K.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..c7a9244 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee2df9ca84525b062c886457915609f47466bc4ae21aab8f939cd809dee7c09 +size 3333401920 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_L.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5a68e46 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb19630a1a43fe919771ee691aa35344087640a48e437b304558276fe8c06c3 +size 4537102464 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5e6808f --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d61fc12038f4b2a5ea8a3cf2cd20857d7fda1ba7d19bd34226be359f9b90912 +size 4209160320 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..33f18e8 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d717ec9ba8d3026b9a6c520ae947298eff61fe6cee61ad5edc0b38abbf62b1f6 +size 3834228864 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_0.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..479d3c7 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467f501f30fe8406a76b5da7a91417639c8a5c7c98b1052762046200e69ba674 +size 4895126720 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..508eef5 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770dcb2c452e91563b6f9d0e596e9f8865b75e5f4639a3c345faa28b0b974e57 +size 5145310400 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..373bb4d --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3665f4ec8c5ec193cfbd99b4470a1a608f965b52c3ea2e9290e4153a46d9a7 +size 4911969472 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_M.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c2ee021 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c965decfef8903887870d841400f67696adfea6120f7a2bf24b5fa1586372a4 +size 6001473728 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_S.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6879628 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8959aa9f5bd320c8ead81af3b7ac334f397ee70cbe278980c89fd261f52b041 +size 5864995008 diff --git a/Mistral-NeMo-Minitron-8B-Chat.i1-Q6_K.gguf b/Mistral-NeMo-Minitron-8B-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..97f3693 --- /dev/null +++ b/Mistral-NeMo-Minitron-8B-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349e27bdb1b6a300c7861a0298f70cc8483bb7ff8fd8a359413036e77c21ca84 +size 6911147264 diff --git a/README.md b/README.md new file mode 100644 index 0000000..724e4e8 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: rasyosef/Mistral-NeMo-Minitron-8B-Chat +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +license: other +license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf +license_name: nvidia-open-model-license +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/rasyosef/Mistral-NeMo-Minitron-8B-Chat + + +static quants are available at https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-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/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 5.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 7.0 | 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..935b01a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32dc1c21e40eaa61e59dcb58bfffb3f2f5ecfed2dac2d52aa8f925f475189e5 +size 5784645