commit 4dab619b489471424a2441db7b0e2a1f03c7c403 Author: ModelHub XC Date: Sat Apr 25 04:57:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..18bb714 --- /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 +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..2a48beb --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ea1af68eee249c26f870142582bb4af6d5e3717a62dbe08d0e397e34639da0 +size 924192000 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..7f69b7a --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0ec5e4961325ea0b20b9118a2b52bd1b8cd66c524c87c785a3f9c7600a97847 +size 868158720 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..42dc1cd --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1acfb7aa944fe6f8cd45d29c061cc6e342ca7cc19a68bb460b2c2da6a46cdf +size 1229032704 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..6bf472f --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ecbdbaf0fb26dc335b128e29f3b67444bdd7d57ac144b9d57f0949a55a3ee8 +size 1154321664 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ef04b54 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a010626124cbfaeddd3e928b2ee4e07d5a9f1a3089e4b15115e7af8a5efbf22c +size 1100549376 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XXS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6ef0ba6 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a833c64127b3e77b579102808c3703ccf8dc34c4aa016e35abc7e310aeadab +size 1017580800 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..b7598dc --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6882a5e64b839bee67796393df6d29b18a431237d6ea52d60eb7c731cd7debb +size 1599669504 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..d106659 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b64dc89be976003461cd35dd656895b8b28a7841d164f2079e7b3f500c0bc21 +size 1542849792 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c3039c9 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b107ad679e3b9e991855e123cd4f5e1d6d5dc31eab06624d7fcd73a5c71b20c5 +size 1476789504 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XXS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..94e31c3 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875761dfcb17c5018f33daa05a4a9d95aa3f37816d9aba963c1b74b560e8124e +size 1348766976 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_NL.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..60c32d2 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097ed69ad455052c9a068072e505f26487fedb4bb176b46f599b54db7c876d74 +size 1917191424 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_XS.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..5d68b7a --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e65ed9cbba722e20104ff8ad68584278cdf6712cac6ca81d3dd1f297c0f9463 +size 1829111040 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..1e17405 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bcf8711b1861d53f8c86b782a28a68d850e574b8b51de4d2ad07fec4b2a8567 +size 1363936512 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f13bdd4 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676c382d0b81c110212a2277608c926b3f8c93aa7371160e6d764862d76441e1 +size 1274283264 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_L.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..62823a0 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac6dd48ec9763d4f77321928e48961abe15a0522584772905f0750ca169db65 +size 1815348480 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4af06c6 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:434bce650a90bbd69ee49ef488ec4cd161764039a763ba4f15a34955b2c136ff +size 1687160064 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..839dd03 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4da8d8d20dd41964d8cd9ac2487d4d3a79e8c6077c10b1b12f025df9600a73a +size 1542849792 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_0.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..31ac8a1 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699478ed8ea199da7127a72a30b4a9260b290b9f62101912868451f19729ea6a +size 1921910016 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_1.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..eaece68 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7749423f77f954224739b3699d6a38336d25be600018571c7265b17c6e6793 +size 2093352192 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..932ce6b --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eadcacfced27bd38af44200bd2bb07138931ec607e5bc166811c9a3946bc163 +size 2019378432 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b0e970a --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a09e491c3125611758dbcdcd08633331f94ddd231fc0a55f0819cba57cd1233 +size 1928201472 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_M.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..db72724 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69577cf47342465ea25cfed5798a4e19e2b41be3dc9cadfb64840279c1831aa +size 2322154752 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_S.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..28bebbc --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5e4b51085b6d8e439d0aab6901feac6c06dc8eb01095593e6393beace34c47 +size 2269512960 diff --git a/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q6_K.gguf b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..a86925a --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1180626f4095f7437884a79e75234c300a8a52a5e5e1ca245941bb264a78e0c1 +size 2643854592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a96a4ae --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: DavidAU/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cot +- deepseek +- Llama 3.2 +- 128k context +- fine tune +- llama-3 +- llama-3.2 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/DavidAU/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B + + +static quants are available at https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-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/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-ShiningValiant2-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..47e529e --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da46d62851c42037e500bf4fe294aca917ab47bc154d216203642694fb087d4 +size 2988377