commit f225aa3634cd294150dee64774b962bd9a6f5779 Author: ModelHub XC Date: Mon Jul 20 04:50:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-32B-Uncensored-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f6313b --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B-Uncensored.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-32B-Uncensored.i1-IQ1_M.gguf b/Qwen3-32B-Uncensored.i1-IQ1_M.gguf new file mode 100644 index 0000000..203e0cc --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42c0d1e23251afc5059cb62919b52917d5a951b526f234e9ae7abed0e892bc9c +size 7959869376 diff --git a/Qwen3-32B-Uncensored.i1-IQ1_S.gguf b/Qwen3-32B-Uncensored.i1-IQ1_S.gguf new file mode 100644 index 0000000..905a76e --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d3c5b55c5db4e6181d338e4c968c5660a5153cf9fd551fff1a24a5e3c87098 +size 7323842496 diff --git a/Qwen3-32B-Uncensored.i1-IQ2_M.gguf b/Qwen3-32B-Uncensored.i1-IQ2_M.gguf new file mode 100644 index 0000000..e846cc8 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e4dfa59b5469f81c46c11644fb7eb435eb0edd41fcc9ba882dc8d0cc3e943e +size 11362862016 diff --git a/Qwen3-32B-Uncensored.i1-IQ2_S.gguf b/Qwen3-32B-Uncensored.i1-IQ2_S.gguf new file mode 100644 index 0000000..12653aa --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599369424fbdfca579dc5565d6fce4d623fa42f476975fac17da4e37505f037f +size 10514826176 diff --git a/Qwen3-32B-Uncensored.i1-IQ2_XS.gguf b/Qwen3-32B-Uncensored.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d66d859 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8aacd1da15ac39dd6e6ef300570c2f396d4a946fb334ecb835c530cc42695d0 +size 9951836096 diff --git a/Qwen3-32B-Uncensored.i1-IQ2_XXS.gguf b/Qwen3-32B-Uncensored.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..92e6bc1 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586ca8c1e42651e541b5d87901f67efc3034f9569a6dcb8165c11b59d6a61139 +size 9019914176 diff --git a/Qwen3-32B-Uncensored.i1-IQ3_M.gguf b/Qwen3-32B-Uncensored.i1-IQ3_M.gguf new file mode 100644 index 0000000..9fc2d2c --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a4e6134855bff4f552c02694d8c72a3af8caa9ea9056bd8ace79dd14f5b332 +size 14930083776 diff --git a/Qwen3-32B-Uncensored.i1-IQ3_S.gguf b/Qwen3-32B-Uncensored.i1-IQ3_S.gguf new file mode 100644 index 0000000..41e760a --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f08c636dc827c1590185946a6b2e8dd15b6081138b06807e96586ca9a0d07e27 +size 14434303936 diff --git a/Qwen3-32B-Uncensored.i1-IQ3_XS.gguf b/Qwen3-32B-Uncensored.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d6c8964 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe1153ac8adfa5df84e24475b6a0da8581bcfb436cb6e1fd80049fa1c21162e +size 13702922176 diff --git a/Qwen3-32B-Uncensored.i1-IQ3_XXS.gguf b/Qwen3-32B-Uncensored.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..521c797 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44685bd1d17e47455d94fed4e8ec29a4b3b9deee0e263ea412bdf232ed7b2bb4 +size 12821038016 diff --git a/Qwen3-32B-Uncensored.i1-IQ4_XS.gguf b/Qwen3-32B-Uncensored.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f05bcaa --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4957b852e623cbcb9565388f321eae887915fe615fce55593371e8a6dc9cff63 +size 17690495936 diff --git a/Qwen3-32B-Uncensored.i1-Q2_K.gguf b/Qwen3-32B-Uncensored.i1-Q2_K.gguf new file mode 100644 index 0000000..c91cdba --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5c4e0c2f0d4653205b61ed2995d7e54a32bdebdb8d303f7a5382b9465c251a +size 12344652736 diff --git a/Qwen3-32B-Uncensored.i1-Q2_K_S.gguf b/Qwen3-32B-Uncensored.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8214031 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b7ddbbd3e1328a54ce2c2165034cc4017de4ba6a6420d4e5229b0f6835a9c8 +size 11465814976 diff --git a/Qwen3-32B-Uncensored.i1-Q3_K_L.gguf b/Qwen3-32B-Uncensored.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9f55a7e --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea33506cf1a26ce40c3f32f270c78439bff984b7db53ad4ed45e3edba81e2cdb +size 17330995136 diff --git a/Qwen3-32B-Uncensored.i1-Q3_K_M.gguf b/Qwen3-32B-Uncensored.i1-Q3_K_M.gguf new file mode 100644 index 0000000..81fa6b1 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d556f6f615e67a7935431d365df822f33c6d7f461e4a66e45ad63fbdd68fcef4 +size 15971778496 diff --git a/Qwen3-32B-Uncensored.i1-Q3_K_S.gguf b/Qwen3-32B-Uncensored.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c79e928 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3922e98b780135932a037c6a3b56cddf97b4b7388af8b4241d3a626a836149ca +size 14389739456 diff --git a/Qwen3-32B-Uncensored.i1-Q4_0.gguf b/Qwen3-32B-Uncensored.i1-Q4_0.gguf new file mode 100644 index 0000000..cd4a743 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04569d8599b7b12758f2bdc1b62135b95724f6d14fad720398651ba8992a556 +size 18703088576 diff --git a/Qwen3-32B-Uncensored.i1-Q4_1.gguf b/Qwen3-32B-Uncensored.i1-Q4_1.gguf new file mode 100644 index 0000000..731b71d --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1807279ef5d725b3038087101381093b77fa0dba02e19c15e3614e825b3ab2 +size 20636523456 diff --git a/Qwen3-32B-Uncensored.i1-Q4_K_M.gguf b/Qwen3-32B-Uncensored.i1-Q4_K_M.gguf new file mode 100644 index 0000000..007afcb --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d972c764d679543ddb89a08feacba394bc65b08ec68daf12d748ce06b777dbed +size 19762150336 diff --git a/Qwen3-32B-Uncensored.i1-Q4_K_S.gguf b/Qwen3-32B-Uncensored.i1-Q4_K_S.gguf new file mode 100644 index 0000000..39faab6 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ca6672cef277813a36fdecaa4c5ca38dea3a654c7cc9930fb06e8aad6cd282 +size 18771246016 diff --git a/Qwen3-32B-Uncensored.i1-Q5_K_M.gguf b/Qwen3-32B-Uncensored.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d98773f --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3174c63ff1ec901a923554b3f1cefdfe4eae921dbd74ab9635946e66d27282db +size 23214832576 diff --git a/Qwen3-32B-Uncensored.i1-Q5_K_S.gguf b/Qwen3-32B-Uncensored.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3538e52 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355ae7c8093558e0a9376a5d693b91a46720b31f7a3bc8642736873a2916e058 +size 22635494336 diff --git a/Qwen3-32B-Uncensored.i1-Q6_K.gguf b/Qwen3-32B-Uncensored.i1-Q6_K.gguf new file mode 100644 index 0000000..1e704c6 --- /dev/null +++ b/Qwen3-32B-Uncensored.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3260c96027f80c318d5ff6fde657c6864b5e9b1d17fd673bf29ff0f644e0ea03 +size 26883307456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3c61ff --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: nicoboss/Qwen3-32B-Uncensored +datasets: +- Guilherme34/uncensor +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nicoboss/Qwen3-32B-Uncensored + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-32B-Uncensored-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-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/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 11.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-32B-Uncensored-i1-GGUF/resolve/main/Qwen3-32B-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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..2424b53 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46e06a8001cc7fc78b407d4f6f8e43aa841287395b7c2811880fde53887062d +size 15219229