commit 3fa27301de3b7e2cd300f3537a4a74787a79f0b5 Author: ModelHub XC Date: Fri May 8 23:23:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AI21-Jamba2-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0586315 --- /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-Jamba2-3B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AI21-Jamba2-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AI21-Jamba2-3B.i1-IQ1_M.gguf b/AI21-Jamba2-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..b6d992d --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c230e41ce37311fd583ff5fe9440dbfddefd52a536e290cc6b081c2332f758 +size 824879904 diff --git a/AI21-Jamba2-3B.i1-IQ1_S.gguf b/AI21-Jamba2-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..476c73e --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cee5bc63ff04bf491bd9cbd7357881c60639a74af146fcbbc75ddd4f8fe927e +size 760183584 diff --git a/AI21-Jamba2-3B.i1-IQ2_M.gguf b/AI21-Jamba2-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..8f40d6d --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550b575a1ecd171a7e795727449bf8f07e22d574a2b5dcdfacfab712fd702f00 +size 1130979104 diff --git a/AI21-Jamba2-3B.i1-IQ2_S.gguf b/AI21-Jamba2-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..de1c11e --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deaea60b1f180dc6a5490a50e82640ecac92de21a84d55a2722c95e33c813a0c +size 1044717344 diff --git a/AI21-Jamba2-3B.i1-IQ2_XS.gguf b/AI21-Jamba2-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e8712d8 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a899b18ffeac98bb7bc08a973e3ca0e74bb50c5a748b78eb7746b2d9cac21a2 +size 1019378464 diff --git a/AI21-Jamba2-3B.i1-IQ2_XXS.gguf b/AI21-Jamba2-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c91ab3c --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd9c8ce0bb8747a6a6898da3e682caa0289c74185ad3289bd1d90a2f7767b75f +size 932707104 diff --git a/AI21-Jamba2-3B.i1-IQ3_M.gguf b/AI21-Jamba2-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..35a5b46 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a60aa9d27aaa19d5cf54a2bb3f3e42ce06343afa03c6233e8ea15c56400997 +size 1465361184 diff --git a/AI21-Jamba2-3B.i1-IQ3_S.gguf b/AI21-Jamba2-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..816ef19 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9130a994528f4fdf849b6b269273c977b82455fd92982214cc4867531ec4e34 +size 1455177504 diff --git a/AI21-Jamba2-3B.i1-IQ3_XS.gguf b/AI21-Jamba2-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0f64856 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916c2c0b037a6da91e4ad08d6758effac69a445f885b80720bf90013a601307c +size 1413244704 diff --git a/AI21-Jamba2-3B.i1-IQ3_XXS.gguf b/AI21-Jamba2-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e7aff5a --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678b25f82eb5308c03dbfdcd87777232b2a299b7486968baca3cc8a8ccb2d5f1 +size 1299662624 diff --git a/AI21-Jamba2-3B.i1-IQ4_NL.gguf b/AI21-Jamba2-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6cbe8e0 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073f26a2282b7275ef2f53d287c904bfd6474d0377578e8109f191935da58b5a +size 1854255904 diff --git a/AI21-Jamba2-3B.i1-IQ4_XS.gguf b/AI21-Jamba2-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d1855d1 --- /dev/null +++ b/AI21-Jamba2-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f42b453ec0228f1d5bc4bbee550fbab2a87063aade111134c1e6b0185caf4c9 +size 1760355104 diff --git a/AI21-Jamba2-3B.i1-Q2_K.gguf b/AI21-Jamba2-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..7767c79 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d35229b126879f1386f5e74fc2546dadab96a7e27b5a9d001d52130722e5e1 +size 1211035424 diff --git a/AI21-Jamba2-3B.i1-Q2_K_S.gguf b/AI21-Jamba2-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0d4b8da --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c7ae0acf1fcbc79c29d0cbe057fe4d88ed8e78911e6692d5b6fe57f7e38c27 +size 1164745504 diff --git a/AI21-Jamba2-3B.i1-Q3_K_L.gguf b/AI21-Jamba2-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..05a03b9 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3910c214dab3f2a07369ffdc9b1572f1964f1f9857850347c911f7ea8ff27e9 +size 1610113824 diff --git a/AI21-Jamba2-3B.i1-Q3_K_M.gguf b/AI21-Jamba2-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f491dd9 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c89329a3d111d74daa4838f94e46ebfbedc2abddb4c22cbea97c5884d9c1810 +size 1537696544 diff --git a/AI21-Jamba2-3B.i1-Q3_K_S.gguf b/AI21-Jamba2-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a0a9085 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d444aedf925364d19e61f883ba29aec275a163a1b6b04f104957e66b1c7b38 +size 1455177504 diff --git a/AI21-Jamba2-3B.i1-Q4_0.gguf b/AI21-Jamba2-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..24ff767 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77b480d045648ab251b717a14dc8f1e5d4121fc3772e5698c8d8a5a65e4bacd +size 1858188064 diff --git a/AI21-Jamba2-3B.i1-Q4_1.gguf b/AI21-Jamba2-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..267dfa4 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825319acf7de8f7c21061f9535c9ee24d5a2615b3072bc8dc87ee4a65ff56240 +size 2043388704 diff --git a/AI21-Jamba2-3B.i1-Q4_K_M.gguf b/AI21-Jamba2-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a6522b4 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff0e11be4a1ee0c40e5564bd4ed9ff6cf3cdee8694cc69579f6c368f8b1d005 +size 1932696864 diff --git a/AI21-Jamba2-3B.i1-Q4_K_S.gguf b/AI21-Jamba2-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9296ed5 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c23f2bc713da07534f64d221394c7cb39d0a7e1c3a99bca4b74fa5e0cb2ad2 +size 1864864544 diff --git a/AI21-Jamba2-3B.i1-Q5_K_M.gguf b/AI21-Jamba2-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d2f4b64 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0252314568443ad669bb6498940a091a74eea73dee5a8f5bcdd84c2ed026390 +size 2272890144 diff --git a/AI21-Jamba2-3B.i1-Q5_K_S.gguf b/AI21-Jamba2-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b4bb6a7 --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da52b49baaf0bc45986729ce236c5e9cca2b5f3912d31970fe67864041565fd +size 2233852704 diff --git a/AI21-Jamba2-3B.i1-Q6_K.gguf b/AI21-Jamba2-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..a6d206c --- /dev/null +++ b/AI21-Jamba2-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998d7163d8c8babbb6c00468043540d09b424ca917135fea9eb5d2d8fdf42b28 +size 2639587104 diff --git a/AI21-Jamba2-3B.imatrix.gguf b/AI21-Jamba2-3B.imatrix.gguf new file mode 100644 index 0000000..6ee2e3c --- /dev/null +++ b/AI21-Jamba2-3B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4029a787dc4a16efd89ed0eaf786476db243504ea3fa1a7f93b3ac3dd1845c +size 2950624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c5c21c --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: ai21labs/AI21-Jamba2-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ai21labs/AI21-Jamba2-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AI21-Jamba2-3B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/AI21-Jamba2-3B-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-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.3 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/AI21-Jamba2-3B-i1-GGUF/resolve/main/AI21-Jamba2-3B.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. + +