commit 102cd4ecc715cb508de38a914b578e00cd9645fb Author: ModelHub XC Date: Sun May 10 05:46:05 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d9f63e8 --- /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 +FFT-IBM-Granite-4.0-micro.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FFT-IBM-Granite-4.0-micro.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ1_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ1_M.gguf new file mode 100644 index 0000000..649afa8 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eae7b69c02c36fc1624c6d401985adfbba26bdbe53e0563459c027fd6a0e85 +size 908877920 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ1_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ1_S.gguf new file mode 100644 index 0000000..87b88af --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f1db4affd33621687dab847c0b6fa94d0e6fd0ff8211629db33fa9b46a7b40 +size 844980320 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ2_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ2_M.gguf new file mode 100644 index 0000000..af74a40 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6955b403c5800a970897d3d55286be7e4ebc8e00af41b05dc66f35b9bb15ece7 +size 1241473120 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ2_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ2_S.gguf new file mode 100644 index 0000000..1fdf161 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e03fdd4f2da37f8cfd81d8d4510a840bba21fe0c16432bf25f9fcd7456ffbe +size 1156276320 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ2_XS.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ2_XS.gguf new file mode 100644 index 0000000..78c6f2b --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a179c2653193125291c6aaa16c940b2e3bad1c3a2956e0cacfee26c07a1d7a +size 1108762720 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ2_XXS.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fc9dbf7 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02460ecf5d0ba764cb9424f73ad94b618cd05384f2e61571532023c3c35a1dfe +size 1015373920 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ3_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ3_M.gguf new file mode 100644 index 0000000..70d2053 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da51f92efd556cb220d9824417890a4e149bc8831e3e61e02b1655030f9994d +size 1622524000 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ3_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ3_S.gguf new file mode 100644 index 0000000..098f7dd --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591eda45fb66f8ce74a8805ea0173c85651a52731591ab8a430d4c01101b0b28 +size 1573781600 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ3_XS.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f8798e4 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbcff39b545bb4077935f913a0a86d689f23d6c1c87dfad6656ee02c41a4a0b +size 1500053600 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ3_XXS.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c4fbf07 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f991c4824a369df54f2f25aee410924bc453472eb748053c07bbb7aa58d41b0b +size 1387290720 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ4_NL.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ed2d43e --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655ca117d21b377beb8594e22a8287d28eb344ea8eaf09e5f53ec596f1bf9733 +size 1991164000 diff --git a/FFT-IBM-Granite-4.0-micro.i1-IQ4_XS.gguf b/FFT-IBM-Granite-4.0-micro.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0f76806 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b816f46aa8740af3ec490075a954d55ac4694f716899ada5eb4bacf0beb8d3b +size 1894498400 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q2_K.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q2_K.gguf new file mode 100644 index 0000000..5879fb9 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3c76349ea59ce228ab3ae572ada57f29be54d20a7d757596b887bf94521024 +size 1371439200 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q2_K_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8294c84 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb899aa49889f47935f030a6f602a9cd779e20e93fea4c470186b4503051adf +size 1284194400 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q3_K_L.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7a38a9f --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449d0b1d149b8f85d976ce60c47ba1ac7355feeeb1f6f44e27b3a4a635370b99 +size 1864188000 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q3_K_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_M.gguf new file mode 100644 index 0000000..eebc591 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d6ff63517544c1981cb3d5c050aaff44e40df58f98ed4f2d4359c0c28cfcfb +size 1725579360 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q3_K_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_S.gguf new file mode 100644 index 0000000..18f7157 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4539eeb3a355df1139ee152f232c66d2edb30695b85ebad4a4334dfcf7438f +size 1566818400 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q4_0.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q4_0.gguf new file mode 100644 index 0000000..5380b6f --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a761197f66cdde20902791b3ca4c7b0f885c9009b157cbe2e4801ce4aabdfb5 +size 1991164000 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q4_1.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q4_1.gguf new file mode 100644 index 0000000..86c47b4 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cc9af8def58529f2a7580df28e540129828c99bb6d43a29d571da81fc380d9 +size 2181218400 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q4_K_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ed1f5c3 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c368a98d38c28c8336c82f1c111f2b16e2514fd46b73eeaa536a03c86331f5c +size 2099503200 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q4_K_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8ee7af9 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f36231f245af6452b16dafa035818810f6d587b6676078b613c571676faf5e0 +size 1998372960 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q5_K_M.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e9a1f87 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a64ecfd576e8074c2db16e801e7b50d37828def1eaace98f6fe3e79a96a828 +size 2437013600 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q5_K_S.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q5_K_S.gguf new file mode 100644 index 0000000..97ab1f0 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f508ef7d597eb9c2e080f96a320d14ed4872b916d08787c5925a54c1e5feb4e +size 2377826400 diff --git a/FFT-IBM-Granite-4.0-micro.i1-Q6_K.gguf b/FFT-IBM-Granite-4.0-micro.i1-Q6_K.gguf new file mode 100644 index 0000000..173b645 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae2d3a11cbf2cdc8ee3644e67c2b9894a695ccd09d30c2d7bd1ed5d5c933e6a +size 2795618400 diff --git a/FFT-IBM-Granite-4.0-micro.imatrix.gguf b/FFT-IBM-Granite-4.0-micro.imatrix.gguf new file mode 100644 index 0000000..c4a0a53 --- /dev/null +++ b/FFT-IBM-Granite-4.0-micro.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ab7b7a90f1de539753db831bdfbf5fc095e71ad6e89055dc82be06f4032c56 +size 3811392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ae6732 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: bdstar/FFT-IBM-Granite-4.0-micro +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/bdstar/FFT-IBM-Granite-4.0-micro + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FFT-IBM-Granite-4.0-micro-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-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/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ3_S.gguf) | i1-IQ3_S | 1.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.1 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q4_0.gguf) | i1-Q4_0 | 2.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q4_1.gguf) | i1-Q4_1 | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/FFT-IBM-Granite-4.0-micro-i1-GGUF/resolve/main/FFT-IBM-Granite-4.0-micro.i1-Q6_K.gguf) | i1-Q6_K | 2.9 | 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. + +