commit cf6576908887bbad9317db602424a51f448b8e79 Author: ModelHub XC Date: Sat Sep 26 23:37:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5833e21 --- /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 +OLMo-2-1124-7B-Instruct-preview.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct-preview.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_M.gguf new file mode 100644 index 0000000..57192d3 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7f5710a5917eecefd9d30d2ce1296c629c33feb0dc7b5b44fd1c9643a817a4 +size 1939185664 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_S.gguf new file mode 100644 index 0000000..46f3db9 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759ef585a42417a615c09b267b7e001b1631e21396a79b93e22a0c3bcaed9eea +size 1816797184 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_M.gguf new file mode 100644 index 0000000..34fe0d5 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb0938cb8483f893809b9a269177c2436be5861072b27a714c665bf0d3c5991 +size 2676400128 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_S.gguf new file mode 100644 index 0000000..8b96407 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bdee0cdf80132294cc1360b0ad75f1bd8fcc29c8adda4524a243424f18d54ee +size 2513215488 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XS.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1abd01b --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d70676144cdb069a5cbf196c78da89ecf7e9f0564a21d99a3e2a6304bd53a5 +size 2323128320 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XXS.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a51d34c --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5f262d3242f866dd46a091f5d6b25ac3bf59aa59801c449f283e585780c173 +size 2143166464 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_M.gguf new file mode 100644 index 0000000..86c97d0 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b571b81e02a74b7a3ce4be7cc1a92b25cfffeb5d79426edfdc4729ebd3943a65 +size 3468697600 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_S.gguf new file mode 100644 index 0000000..c505cac --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4da968c3769bfa4853a0f10a1be347f037c586cdccfd8d890db8148ddf932ce +size 3302137856 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XS.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3b29c65 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ebca9b6dd7b676310f73a6e6491263037329976e8a1e728098f48cc9def971 +size 3150356480 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XXS.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3114be8 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f045ca487c263fcc61bf603c8bcd2bcbf3216d2964120153926e68a30e218424 +size 2902040576 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_NL.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cfbda91 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1a4a3df741fb7ce9723ec638b19926b59342199c101cea9a98f79d7b5d5630 +size 4216823808 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_XS.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8ae22a6 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5550cb0fc8761d2b664d1d6b5788b2b31583bf03f3292bb28186e58ff1acf35 +size 4001603584 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K.gguf new file mode 100644 index 0000000..7565d37 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0907205eed7bb1097006d54b126eb4a7b8b5de886c065be3b05bada54f8c6716 +size 2858262528 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K_S.gguf new file mode 100644 index 0000000..beaf0dc --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bde38132ded265eb4bcad7ab26483d16138950fa15704d02039b24ed4ebc92 +size 2644942848 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_L.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2321719 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c6d62e6bce16c20d6798f00cdbc027d95eb77d42e990c47552e4c6dabada2b +size 3950944256 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b6b8e54 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a526e4a55f995ae0f9b70373c38a0628ddaf6a3686039ed7202c018747be08b7 +size 3651837952 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6c54f0d --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370c432faac969b183f537b4ca8490dbb12eb613569c323099566767fcbaaf62 +size 3302137856 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q4_0.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_0.gguf new file mode 100644 index 0000000..9b7d485 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fbba1f90b2b9ef1daade13bc507bf62be407d50f91a722be5b572efc961c59 +size 4228096000 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q4_1.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_1.gguf new file mode 100644 index 0000000..9b26c3d --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdb217a9d4c1bcf9ff1d5983fb6f0f5d7262b6ed9c1dbc745a52a634889dc933 +size 4647264256 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_M.gguf new file mode 100644 index 0000000..36c41bf --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b4670fc1fa4d5e4b997bcdb6e6b4d027a289d2477bbbaafdce33ce0a8fd703 +size 4472020992 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fe89ae7 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c477b9bcfb969b361ba12276c36fd3a33600c5c59419db613343c1ea9f56a4 +size 4247756800 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_M.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cf8eb1a --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472977ff0d9b427bbed402b29c17c4f8e400c65c69b7fb71db11338b18b7ee46 +size 5209169920 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_S.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_S.gguf new file mode 100644 index 0000000..881d8d9 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4a62c5832aa9c776855036401cb2add86f7e999b6a01ff149acca7c91d0c40d +size 5077704704 diff --git a/OLMo-2-1124-7B-Instruct-preview.i1-Q6_K.gguf b/OLMo-2-1124-7B-Instruct-preview.i1-Q6_K.gguf new file mode 100644 index 0000000..4c66f6d --- /dev/null +++ b/OLMo-2-1124-7B-Instruct-preview.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8665766eacc84d86e745c4b265aa854e2a492265ddf6e6bd0675c503a3e83315 +size 5992390656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..31dab1d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: allenai/OLMo-2-1124-7B-Instruct-preview +datasets: +- allenai/RLVR-GSM +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct-preview + + +static quants are available at https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-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/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_S.gguf) | i1-IQ1_S | 1.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ1_M.gguf) | i1-IQ1_M | 2.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_S.gguf) | i1-IQ2_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ2_M.gguf) | i1-IQ2_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q2_K.gguf) | i1-Q2_K | 3.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_S.gguf) | i1-IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ3_M.gguf) | i1-IQ3_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q4_0.gguf) | i1-Q4_0 | 4.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct-preview-i1-GGUF/resolve/main/OLMo-2-1124-7B-Instruct-preview.i1-Q6_K.gguf) | i1-Q6_K | 6.1 | 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..dafcdb2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e0f55de62cd59d8184cb089d87b318233d590acbe665d5d6acf50b1dd3b412 +size 4562173