commit 69cf758561609d6e4cb7624650d673c27a367dc7 Author: ModelHub XC Date: Thu Jun 25 16:19:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Neo-X1-3B-Preview-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..293d641 --- /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 +Neo-X1-3B-Preview.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Neo-X1-3B-Preview.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Neo-X1-3B-Preview.i1-IQ1_M.gguf b/Neo-X1-3B-Preview.i1-IQ1_M.gguf new file mode 100644 index 0000000..99e1f52 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a9312d38d11c40ee306c03efef4dba8ca987a210a7137bbfac097f3563b4b2 +size 850028800 diff --git a/Neo-X1-3B-Preview.i1-IQ1_S.gguf b/Neo-X1-3B-Preview.i1-IQ1_S.gguf new file mode 100644 index 0000000..be68481 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:377b9585395a5f9dade924a158c9f8ecd6c98ec2bfc4cf1568b3108d16377447 +size 791095552 diff --git a/Neo-X1-3B-Preview.i1-IQ2_M.gguf b/Neo-X1-3B-Preview.i1-IQ2_M.gguf new file mode 100644 index 0000000..cd7fa8c --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a07d99e2a8987a0e85fa0d30d4c17cb2150f3d87d4e83b5182969a18fc020b +size 1140517120 diff --git a/Neo-X1-3B-Preview.i1-IQ2_S.gguf b/Neo-X1-3B-Preview.i1-IQ2_S.gguf new file mode 100644 index 0000000..afc62f8 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09db87d59586dd1052df1632e2ea440868a1e5c9253c15354eab84d820d0fe0e +size 1061939456 diff --git a/Neo-X1-3B-Preview.i1-IQ2_XS.gguf b/Neo-X1-3B-Preview.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7acc8da --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c68116e82e7480b8fcde776b03eacc16ab182a7b18cb784b20c6283b947ec9f +size 1031547136 diff --git a/Neo-X1-3B-Preview.i1-IQ2_XXS.gguf b/Neo-X1-3B-Preview.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3ef251f --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de19ca1f5579f4e1440e2138de18712631888fa5d355385a9c2edba58571530a +size 948250880 diff --git a/Neo-X1-3B-Preview.i1-IQ3_M.gguf b/Neo-X1-3B-Preview.i1-IQ3_M.gguf new file mode 100644 index 0000000..3d42f86 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c100ead0a4250e3d3fe581cd702c7ea814fcdc048243079138d29aa27d3d8182 +size 1488896256 diff --git a/Neo-X1-3B-Preview.i1-IQ3_S.gguf b/Neo-X1-3B-Preview.i1-IQ3_S.gguf new file mode 100644 index 0000000..d98dcc0 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76318e567851090bd6fa214ccdcc65ba418920c936131b103fadaa1335a400d0 +size 1456865536 diff --git a/Neo-X1-3B-Preview.i1-IQ3_XS.gguf b/Neo-X1-3B-Preview.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ea69341 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85934ae5e5ebd66104768e029d66fe0da29955ea5ab8bf41b64ea369214b32da +size 1391837440 diff --git a/Neo-X1-3B-Preview.i1-IQ3_XXS.gguf b/Neo-X1-3B-Preview.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..595b077 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3573971538befc2d2ce78101d2578809b81460fb9895b1f8a1c25f6cd95e7fd +size 1282828544 diff --git a/Neo-X1-3B-Preview.i1-IQ4_NL.gguf b/Neo-X1-3B-Preview.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6bf1cbb --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c5981d441f38cbc3d2cad95f123d674b81fdaff0943e39f92920a906e1e7ed +size 1825210624 diff --git a/Neo-X1-3B-Preview.i1-IQ4_XS.gguf b/Neo-X1-3B-Preview.i1-IQ4_XS.gguf new file mode 100644 index 0000000..de2a59e --- /dev/null +++ b/Neo-X1-3B-Preview.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0cc383eef5b2d5ccea7d16370a228aca0f7d1ec4f210affe07044ed9e233e24 +size 1739096320 diff --git a/Neo-X1-3B-Preview.i1-Q2_K.gguf b/Neo-X1-3B-Preview.i1-Q2_K.gguf new file mode 100644 index 0000000..c8a14bf --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c410d25ec9996dc5b260fe212a6fc71509eff81548b4863236f117af917463a +size 1274757376 diff --git a/Neo-X1-3B-Preview.i1-Q2_K_S.gguf b/Neo-X1-3B-Preview.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4bcd836 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2999998d8d73002735be82fb4c759060bfbc569543579700edd794feb9dd7bc2 +size 1198129408 diff --git a/Neo-X1-3B-Preview.i1-Q3_K_L.gguf b/Neo-X1-3B-Preview.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2f21565 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0db14b4baa595e097fbfa57be6150d99fd1114ea54f84dac3244558258c6c5b +size 1707393280 diff --git a/Neo-X1-3B-Preview.i1-Q3_K_M.gguf b/Neo-X1-3B-Preview.i1-Q3_K_M.gguf new file mode 100644 index 0000000..529a4e2 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cfcfb9c89b203a5247f85b371bf22b07567da8e0890358d2156d2c1fd1bc0d +size 1590477056 diff --git a/Neo-X1-3B-Preview.i1-Q3_K_S.gguf b/Neo-X1-3B-Preview.i1-Q3_K_S.gguf new file mode 100644 index 0000000..49bbf18 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043f8d281e4ac66f780ada4d32427168d111b14e8807f6eca7ded30a10062756 +size 1454358784 diff --git a/Neo-X1-3B-Preview.i1-Q4_0.gguf b/Neo-X1-3B-Preview.i1-Q4_0.gguf new file mode 100644 index 0000000..ea8215e --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0201a4108a46262e3e2d9fca644c4465c85984430da094608d91995b85dcdcab +size 1828487424 diff --git a/Neo-X1-3B-Preview.i1-Q4_1.gguf b/Neo-X1-3B-Preview.i1-Q4_1.gguf new file mode 100644 index 0000000..f1bf27e --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a598af9a38dfe53ae4c1cb115acafbd3daceb6d0410860c77eb0cc01e0cfae +size 1996259584 diff --git a/Neo-X1-3B-Preview.i1-Q4_K_M.gguf b/Neo-X1-3B-Preview.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8c8fb80 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c855422ba47912c31b4ff0385a5542980c2fdc08ce6ae10111eb6804a7dc1cc +size 1929904384 diff --git a/Neo-X1-3B-Preview.i1-Q4_K_S.gguf b/Neo-X1-3B-Preview.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e5e1e59 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c21c0bf2802800e30adbab990464438bd431fc39a713bcb08caacbdc917f9e +size 1834385664 diff --git a/Neo-X1-3B-Preview.i1-Q5_K_M.gguf b/Neo-X1-3B-Preview.i1-Q5_K_M.gguf new file mode 100644 index 0000000..853de66 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2411d1504b9231ad75a46ad0b7cee6870ea95377f1905b4b47c925f8c4608b5 +size 2224816384 diff --git a/Neo-X1-3B-Preview.i1-Q5_K_S.gguf b/Neo-X1-3B-Preview.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0d092bf --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369b348d7a1304fed67ddb9e2c2931cae999bce20e70c0b9d4d403a8ca7372ab +size 2169667840 diff --git a/Neo-X1-3B-Preview.i1-Q6_K.gguf b/Neo-X1-3B-Preview.i1-Q6_K.gguf new file mode 100644 index 0000000..74cccb7 --- /dev/null +++ b/Neo-X1-3B-Preview.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310a736171a8a49d1543ac66b626d9cb42332802704ab08a7c8370fc40cfc25a +size 2538160384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6cae31f --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: open-neo/Neo-X1-3B-Preview +datasets: +- BAAI/TACO +- rubenroy/GammaCorpus-chat-70k +- codeparrot/apps +language: +- en +library_name: transformers +license: other +license_link: LICENSE.md +license_name: neo-research +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- qwen2 +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/open-neo/Neo-X1-3B-Preview + + +static quants are available at https://huggingface.co/mradermacher/Neo-X1-3B-Preview-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/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Neo-X1-3B-Preview-i1-GGUF/resolve/main/Neo-X1-3B-Preview.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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..cbe72e8 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6495ffaeb2f0220cebf7be4a7614119d44aabe0078b1bef5153d10ec9283731d +size 3362977