commit a3cd07dce75fca394594900400110a6ea8caff8d Author: ModelHub XC Date: Fri May 1 16:59:31 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45a03ab --- /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 +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..ee82ea6 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045052a5d670342ac3e1748eaf35ff6a31dc203eea41967ff349f3b9c19e9c56 +size 2161977568 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..0c6ce8c --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:908e4d6816a44feac473327a0737473f8b16df725c51c0498144c6b06c2c8690 +size 2019633376 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..42568e2 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e9fed2ca021dd149bd25b3cf99b99cd6ac7d85452a8d7c668fe66320dbc2b8 +size 2948286688 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..0006a5c --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b41c0f701ae32e6c98ff3d902fc25465e86c43bb3fc821f8f885d9ebf48795 +size 2758494432 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XS.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..98e547a --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c8f822ecc6f28242c90d18f02a4cc2bbc7a8210e35f4297fc923523da308c2 +size 2605787360 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XXS.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3b96c64 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59368e2dfdefa8cd792a40cd3666d9f9a79ab19d99a7371c99f9a2e61ae0e071 +size 2399217888 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..6de232f --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0459276f00038e0ee64ff1cd82e27ad99db423f7c6348918952603be07d1d6 +size 3784829152 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1353456 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c739cf30bf2853fd2664e8f864f16714aa1e6e4072a9c02ad9c4a7e5860511d3 +size 3682330848 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XS.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e85e3ce --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500474b516b2e9f186fdc7032decb2f7f781c9e6daa2d85f92b51e44a3bb05fb +size 3518752992 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XXS.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3744b4c --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6b80a3a29576e2251abe2cd6f4b7277acb5de0ba1d17f754b67130cfb648e0 +size 3274918112 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_NL.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6917375 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d00f26b13e16d14e1a78bd9ca782baa8b207796462bc14e472ae3ab6e7e29e +size 4677994720 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_XS.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8432ab2 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e597dfcb244c3a637e39abded175a2bb628b94b75d6c6cc8aa4724b123d736a +size 4447668448 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..ac31ad4 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3ee637a57823f9ed9c1b4b43162e6598c8cd4feb4f9e380b21e9d2b9e99c50 +size 3179137248 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..475ed61 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa4b57622af842ffb9046b01169d469c19eeb60a8a9255650a23a701403b5f8 +size 2988820704 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_L.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0b530e9 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94038a79c7b83f0f48fe9852c168847fc8f09b86594534a026cc96d1446af476 +size 4321962208 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b2d9681 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3286347db3501c32e84c1110f9980e0c80d2c558588b4b9c393496eb0814367f +size 4018923744 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0812654 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f9967e7f49b81be6830f76c071f457f9ab03f59017d788e9faf29841dc0ce4 +size 3664505056 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_0.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..b71717f --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:852aaae35b4774ad7b7f46c0afc4377451b0ed9fde9ef70c92573426a7525810 +size 4675897568 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_1.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_1.gguf new file mode 100644 index 0000000..aac3cac --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16097b2c14ebe99c4f07df36e1e1e2b62c4760cbe7d2f69047423f25d26aaf12 +size 5130258656 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a0f58b1 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8490d73f54110d5bafe1dd8d8670f1ca3a5f86d45acd4702d23838e9ae8c348d +size 4920740064 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bf87994 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165051a3b4757aa0e92c6844e6a334fe27190a37401c8acaaa8fa419de4afb59 +size 4692674784 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_M.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8b0bcc8 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e78fc084d0ed8a00c63e9ff78469203eca73d08a17906dab0fb9f462dce12fe +size 5732993248 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_S.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..abbc223 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd41b068334a1f05974547e320af3f0baf05180c9bb1686175c3395e7284bfc6 +size 5599299808 diff --git a/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q6_K.gguf b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..8e57bf3 --- /dev/null +++ b/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cbd6263c3156a6fe86727db5d49cc08389a2596f2fbdb9a895d2da481c15349 +size 6596012256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c244efe --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: DavidAU/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cognitivecomputations +- r1 +- llama 3.1 +- llama-3 +- llama3 +- llama-3.1 +- cot +- deepseek +- Llama 3.1 +- Hermes +- DeepHermes +- 1,000,000 context +- fine tune +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/DavidAU/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-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/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B-i1-GGUF/resolve/main/Llama-3.1-1-million-ctx-DeepHermes-Deep-Reasoning-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..1266855 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663d81f4764b61d228fa2538e75575aaf998b3a29b5be8d79709b3cd9a8ee499 +size 4988157