commit 30877e8aa7047367765c76226874a0002499c448 Author: ModelHub XC Date: Sat Apr 25 08:17:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e7cd0b --- /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 +AI21-Jamba-Reasoning-3B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba-Reasoning-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ1_M.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..c019cd6 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:243ebb69497da9e870906324806532bc3d4f7ba211975015843d5cf17eb357e4 +size 826972800 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ1_S.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..a853f3d --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ded6d9b5c80cc8a029b4956a5ebb8a116bc16aaaca07411a8982d165956560 +size 762276480 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ2_M.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..b4b9afb --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5a25376a7dc3be633ce9ec32ae94dd5ad240d9043b183ff8155a9009d1ff53 +size 1133072000 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ2_S.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..fb666ef --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fda0eb5829ff8edea76a6a2b88872084b58f64ec62ba35e2bd154cb0f363de4 +size 1046810240 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ2_XS.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..24f8112 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80bb4d6ccd6db68271a4d62776038a57e666e609fa268ce545821bd504eafa00 +size 1021471360 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ2_XXS.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..491296f --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb425e428389ce2208ae2750f820123a1847522324c11c9c14c29d7e7d558c3b +size 934800000 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ3_M.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0f10879 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac89f84d42730f26db9e0d9a9aea24e4844d4173da9dca169ff498e629e8949f +size 1467454080 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ3_S.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1a75490 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a3a2aadf7578eebd394b42100b24bc8b393932833747831d42f6880e857e7e +size 1457270400 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ3_XS.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4948479 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f891ae3e836fbed2e105f6ea65eb7eeb9e065577458e4b8fa9ca6649cfa9f541 +size 1415337600 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ3_XXS.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..31dc5e6 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda59f6d402a806ebf85f1652b04171aad18ccf3260a5ef1405f8673e4a71a8f +size 1301755520 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ4_NL.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..055c8f3 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8549af23e1c3406403dafbc185d9ef788416c85271787a2b0eafd241b76fa72b +size 1856348800 diff --git a/AI21-Jamba-Reasoning-3B.i1-IQ4_XS.gguf b/AI21-Jamba-Reasoning-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..84d6251 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba0844fdc46abb14bbeea16685a80c7013be83d52c29b25acb0fb414a90285c +size 1762448000 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q2_K.gguf b/AI21-Jamba-Reasoning-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..8391d28 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20dfd4d0eb5597cece2091cf22acca8a1fc189fe6e0cf7c2f6dbbc65b49af670 +size 1213128320 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q2_K_S.gguf b/AI21-Jamba-Reasoning-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dd5c505 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd483e26fc29f737859d789d646a370b3b47f01091eaa0f5a1080a07edb8abbb +size 1166838400 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q3_K_L.gguf b/AI21-Jamba-Reasoning-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1e657ee --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951db59cb4e266ca8109ae4a78744cd99083aaf14c6b1e649ffcbbff082267fa +size 1612206720 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q3_K_M.gguf b/AI21-Jamba-Reasoning-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..904c60e --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e575d0e8c85dbf29f2ad04467f45c885462b22319d4e6efe8655ba4a3b80c0e1 +size 1539789440 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q3_K_S.gguf b/AI21-Jamba-Reasoning-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..89d4cd2 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9adcd48430c0cee353bc9b4f4d26efc98da85250be64adebcf9a2b8aed9881 +size 1457270400 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q4_0.gguf b/AI21-Jamba-Reasoning-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..fd98686 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f495764f0b937d91c1c14b85efa4d0dc9150ea9e5d21dbbcb1df428ce5e99376 +size 1860280960 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q4_1.gguf b/AI21-Jamba-Reasoning-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..f47ce3e --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0602bd0f9bb9bf0d89152c01b27374b2b46905134402fe4ab7e49b00a07aa133 +size 2045481600 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q4_K_M.gguf b/AI21-Jamba-Reasoning-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a226bf3 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998348b631063e8bb75fe557b8a9c16aed02807bd27ee525761c4fcd42957c3b +size 1934789760 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q4_K_S.gguf b/AI21-Jamba-Reasoning-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bd01567 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329e8ced48edaeeafbd5c54afabe8a90ee23daed20bb5aa2d574e25ed1163a4f +size 1866957440 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q5_K_M.gguf b/AI21-Jamba-Reasoning-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3e39d7b --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12ec92b5b4eb1be35e27835bb0e36b50c10d29b550a4a1e3d95b4f91a63df02 +size 2274983040 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q5_K_S.gguf b/AI21-Jamba-Reasoning-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b2ea891 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bbf4e4a02f5caea543a3a61ec1eec8ba53e3b0c5544646cb53bf63182cfbaa +size 2235945600 diff --git a/AI21-Jamba-Reasoning-3B.i1-Q6_K.gguf b/AI21-Jamba-Reasoning-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..c8e4cb6 --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7b8b3f3958c4da4c4213d2f58b0f578f168672de80d7c6c9d470ed9f5c9743 +size 2641680000 diff --git a/AI21-Jamba-Reasoning-3B.imatrix.gguf b/AI21-Jamba-Reasoning-3B.imatrix.gguf new file mode 100644 index 0000000..49cec3c --- /dev/null +++ b/AI21-Jamba-Reasoning-3B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b65fe25f03772c61ccefb2f04e63a3a5bda1893f732b5b55a9a92a20eaa0408 +size 2950624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8af76dd --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: ai21labs/AI21-Jamba-Reasoning-3B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://www.ai21.com/licenses/jamba-open-model-license +license_name: jamba-open-model-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ai21labs/AI21-Jamba-Reasoning-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AI21-Jamba-Reasoning-3B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-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/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba-Reasoning-3B-i1-GGUF/resolve/main/AI21-Jamba-Reasoning-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. + +