commit 1227789ef25165fcb5af20a881aee339f53e4a07 Author: ModelHub XC Date: Fri Apr 24 10:33:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5fb7399 --- /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-Hermes-3-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..d29fcd9 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0711c715996519818fb91758a6d663088dd4b59f65f617e4c16a747fa8371ecb +size 924187840 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..a52741b --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b220e635e64fc4cb2373800355ee7f8a21a3ccd646d4da205500dda2e536b0c7 +size 868154560 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..36c6828 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d1e3e4a8c196ddb7c4c8319c3ae9d5511d0cff0869cb784f6a7e097b9b0ffd +size 1229028544 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..2f382fc --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41e42b715dcaa891d2a71628def1e6eb97e6063af67eb1d766f78ac30bc2445 +size 1154317504 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XS.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9a40333 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9db965864a35359163e451cca08a946d37501d8cb6b91c5e292fbee073666e +size 1100545216 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XXS.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b8e3032 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4b33aadd39f0ec7ce4e2a9d2f4358ecf48d8998627f2a75c6e684e0facb5e2 +size 1017576640 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..255961d --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4421422a5b02d95c1b187602c790970aa0834619ab01614004581d652e26c466 +size 1599665344 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..91c8462 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56865de1d4cbad9d7b5f0d479f6eccfbc072ec75706688b46ffd2c44658d48c0 +size 1542845632 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XS.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..85f4e3f --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d3cef2443b45715fbdaa29f9cc27ed8d19008aa5911f6620da5f941f5514f7 +size 1476785344 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XXS.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0ef8c5b --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac96915403e472d339a667ae2ceb91bb67a706e2500969de4cd36a31df6fc2bc +size 1348762816 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_NL.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..79276bc --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b21501ee8cd7f346b5077ba44c8f2804dfe78d2ca966cb75b2e61d4d050c6f +size 1917187264 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_XS.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4318d5b --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d965baab5d5d22851355b1b368e79550e431eb3952163bc76bc8774a7dcc540d +size 1829106880 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..3b01bbb --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:808bffd613dc75e1240f59c12e592113877aab90d9b087fe606f639d90d96284 +size 1363932352 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4450126 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ae572107a56ce0c84a3b46db7e8f180901d8f5e1264c55cefec25cd0f1f0d2 +size 1274279104 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_L.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2d72852 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f78a3708fd5b9814cd4405764613fedc395bba3bb08b0c1fd6f5a399aeba3cf +size 1815344320 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..afd11cb --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa07fcc095e51fe86a29afac88b65d57975e784e4ccb80953d9871eaa85e0fe9 +size 1687155904 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7288371 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b273c407ecd3f069363973b774b33065ab7f733c2f4a5d0a198ee472b568ebe9 +size 1542845632 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_0.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..38ce188 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99f004e7907de159beaa0b374ca41345026a1ef31fa1adcb0c3722db0ba6678 +size 1921905856 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_1.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..26ff0b4 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed12066c8a3e645017ac63b9e352fa0d3b346bc2eb0e42d5552c0696592d36c +size 2093348032 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4519e6a --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9995f6951fd5263638e587788b8d593ed5dff4bb397910016e040433226b24e +size 2019374272 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..beb9902 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a81ac86aa55217eaa8c9eb874577152c75a580fa0333fb9509ed3f462dd7150 +size 1928197312 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_M.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..50f2680 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ba08fe8df05e9007a40222c9f93882c5550324f4ffd10191ad9ae6305820b0 +size 2322150592 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_S.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3844675 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9370b35566c88c19f71f97b4545346ef9f23e52a161e411f704b4b3a2ae1b5d1 +size 2269508800 diff --git a/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q6_K.gguf b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..65b62b6 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970ab3849495e2c8ae4d4cca399753a8b9bff433f42724488399d5aca5640358 +size 2643850432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3894c4e --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: DavidAU/Deep-Reasoning-Llama-3.2-Hermes-3-3B +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-Hermes-3-3B + + +static quants are available at https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-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-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.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-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.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-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.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-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.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-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-Hermes-3-3B-i1-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-Hermes-3-3B.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..5ce6306 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbe17cb01dd1018fe0ace328393e048a10eb50debae88ea53b31fde15194f0e +size 2988377