commit 2e865940319467b02088277828be516dae13aa06 Author: ModelHub XC Date: Sun May 31 03:09:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fb833bd --- /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 +Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..d7b5628 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d6a5943cef0a74bed2e4594f8bc06b493aaeaff187ab750ea04c2d40b06880 +size 3849658176 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..f807a96 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a50f3586a5c41f624ef1093b885eee6f67e705a3877e50cae1f25a7d9d4e85 +size 3579936576 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..a227e59 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:069f57fa41bbd466c922742ca42358048aaeb32ab1db5fcf6ed4c5eed663423d +size 5322943296 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..c886f12 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280cb8ab904caee178a83f1028207249ce5744947594cbb5aa9a6a914c290fc2 +size 4963314496 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XS.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e5eee67 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c926d1fc6e9f0d2ac679ab96d7c3d9f1d4117901dbdb0faf695bd382f1d66705 +size 4691590976 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XXS.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bea4eea --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a9fe631c2d94aab84e022027a52ef872c15a5775419d4fb19324e012dba054 +size 4299194176 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..4b4e1dc --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7728d4fcd93469a538aa0437570c7323f7f8af5f93bd9618fc934778e2341e8c +size 6883411776 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..164de52 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ad4b5d6ef1a31e141c3e83f10f4694f0073f4de3af42d70f5274a2c9ac01d3 +size 6684960576 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XS.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0399efc --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d7711ad8dd7b5a2c4ee68805605f1fad8236e6a644575fae048021f65d3889 +size 6375302976 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XXS.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9790778 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62705e9698680db706fd954cd895ce809f29ef6998b4d32bbfc8996318c5ffbf +size 5942668096 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_NL.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..05d0a9d --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e72148a96749dd2a11c4b9a0c2de0a71c5bdc378ada5bccd840780073245df +size 8541365056 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_XS.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..454e4e0 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a443834d0f8eb7e96c08e2749d521eb3513e7902bcd1a386f37ed22050283baa +size 8110732096 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..47ac79a --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79168f72690fbe4aa69c8ea6b21bcc39168af979f26450f7859a6a7a043f35c5 +size 5753985856 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4faba62 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82f8641739e825ca8d2fff91fd1a8cd9db1820f223788e3c871899249ab1ef4 +size 5389851456 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_L.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..dcda710 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54012d320ad6d0688d74ee25bd347f756f7769d3129211d49581cebd732ba38c +size 7900653376 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..81b6b6d --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeda2519ba0a89c9be1db08cc1c761d62f7f3109eeee53e17c8aecd66bfadf63 +size 7321315136 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4677642 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cb4c8cd148e884466aff0e9a774488b1f3330aa0f8b73ff12f06d145401b64 +size 6657107776 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_0.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..495b773 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251b085bfe67f06327bdc9b5fd0ccf839401de1fc0c70dfe75e80d3893d1787a +size 8543003456 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_1.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..e1e8bb5 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8e157f7eec8622fa87e0e3d4c7752b92117703602c9f0c09e97e84631fc589 +size 9389523776 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4d0b63f --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de346b7256af32f5070637544f014507481b1285fe9df35cddece72b52f4842 +size 9001755456 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..940f541 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52351eb024a8f11346dc5d391c46430a50bf7b16628c4e5f9de4d4fde3d53fc0 +size 8573477696 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_M.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7c6cf45 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0590672003515ea5e68e9b557466861596d587df864bf53ccd224f166131a1f9 +size 10514572096 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_S.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d3723f4 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854788a91ddb3fb95dc4974555f0bf914884212f532d1c183cf0bde104a35c51 +size 10263896896 diff --git a/Ophiuchi-Qwen3-14B-Instruct.i1-Q6_K.gguf b/Ophiuchi-Qwen3-14B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..5eb07f6 --- /dev/null +++ b/Ophiuchi-Qwen3-14B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1965c936886112aaecb1e976c620398ad4f8550af6a1c7b3168305051693d995 +size 12121939776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ceac249 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: prithivMLmods/Ophiuchi-Qwen3-14B-Instruct +datasets: +- open-r1/OpenR1-Math-220k +- deepmind/math_dataset +- burtenshaw/tulu-3-sft-personas-code-no-prompt +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- code +- math +- moe +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Ophiuchi-Qwen3-14B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Ophiuchi-Qwen3-14B-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-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/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 3.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ophiuchi-Qwen3-14B-Instruct-i1-GGUF/resolve/main/Ophiuchi-Qwen3-14B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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..6a203fd --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4259ca6934bd20b4159eef900ff730cb24bee8d53e967bcd58034495c1ef8215 +size 7709765