commit 4f089db4a98ddddab090b3833fb13891214e1446 Author: ModelHub XC Date: Sat May 2 01:08:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a52c0b --- /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 +GRAM-LLaMA3.2-3B-RewardModel.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_M.gguf new file mode 100644 index 0000000..4711e83 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ec0471d44cf68e7e3822986d2e874d28efc58a9b97cb597d80d9e158e93113 +size 924192064 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_S.gguf new file mode 100644 index 0000000..198f195 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee9beb04426afa26d1d2cf880f2e151a258d0edacb39ebae0609e2eaa9e2cbb +size 868158784 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_M.gguf new file mode 100644 index 0000000..661c80c --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc81449ee884bbcdb72f3c8cfbd59c308f751ec21a0fcdfed43c3eb3ff62a76f +size 1229032768 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_S.gguf new file mode 100644 index 0000000..16d4ca1 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea8e69eb0152279eb30a9f4dfd4d8e2f0774abe09912df6334392fe13ff01cf +size 1154321728 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e5c2bc7 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c0f8f83c6c141676a7da4864e7cb28db2bb565f980457a9881ee295c0c1a15 +size 1100549440 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XXS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e54aba7 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f75abc4bb63847c9c319e329ec097f6a1d97286c5828440d90d70917995752 +size 1017580864 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_M.gguf new file mode 100644 index 0000000..98995af --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e2820d36b7f86fc00f7e24164e0824739c3a5c1e5206a4fc328a7b55c1d3a0c +size 1599669568 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_S.gguf new file mode 100644 index 0000000..638b9f6 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3692f3f98b0695fa47edf8194e62826876f0b8108bfd4843d99954c4935ba4 +size 1542849856 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7427312 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b29ad4e34f8682fc7c60c92cb6d1286fbfba64ecc14db4b90fd03a3868209d +size 1476789568 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XXS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..38ec2a6 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226b7f74464b4ddf87d65d41618abe054ebfc0b35f2605a9292d50594320c220 +size 1348767040 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_NL.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_NL.gguf new file mode 100644 index 0000000..81883bb --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8c4bb35b41c7b7a356daa408e89904be1c3c15868f153ce4e7112a9f90c73e +size 1917191488 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_XS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b33522a --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d88431cf077a97d51d8f8c15d5ec75f6ed8bfa440ce36386e017eb08ee1723 +size 1829111104 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K.gguf new file mode 100644 index 0000000..e2671bd --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da881aa36975a0a7f61e5a2d9ba30e132e16f277731d66d88a4c39397eaa883f +size 1363936576 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K_S.gguf new file mode 100644 index 0000000..5055d35 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32576fbe9ae58b6a0da8cc4f319cbe3cdc829b3c450210c285055059c807aaf3 +size 1274283328 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_L.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fd31bdc --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195e43558bc5f2f02318c573c6aa40ad3cda32e8b4e59bbdd775c8e5783cb17d +size 1815348544 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fe3c77a --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf74ec9e301491103d394b42c003609d14c96bfcdf6201509472e017f7e8058a +size 1687160128 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_S.gguf new file mode 100644 index 0000000..11537f8 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61a0d1ae7cb18b1f2724db7be2ccf2906530c8435c81ec4301ae34d06befdaf +size 1542849856 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_0.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_0.gguf new file mode 100644 index 0000000..352b240 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0393349e06badac281bd6ef53bba4177c3ad4583663fa721ea9cadfc58c011e4 +size 1921910080 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_1.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_1.gguf new file mode 100644 index 0000000..26f52f4 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ddf9c8c7257346236066aac7676bbb4547353f374ef249b2ffec2864f2478fa +size 2093352256 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_M.gguf new file mode 100644 index 0000000..533834e --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1bdb56352e496c231c468005b8996f31fc01873406335001846b015fd3b96e9 +size 2019378496 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_S.gguf new file mode 100644 index 0000000..00d4280 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b4cfd452ac3282913f6662b78a5048ab66f7b634db394ea2ddce31a4bd9eec +size 1928201536 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c92aef5 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c937b0c08dd64553df4bf197d2d61287cb8d9acefb0609e9a1ced4a7d068fd82 +size 2322154816 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9107259 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254523cb6f367da43804a99b4d0c854d65491ef9e42356d74e1bbfd91c1bd0d1 +size 2269513024 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.i1-Q6_K.gguf b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q6_K.gguf new file mode 100644 index 0000000..cf0160e --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617752068a0a3ab2201d441ba80e23df64b674bc949cd66ea02fefc2c874f8ae +size 2643854656 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.imatrix.gguf b/GRAM-LLaMA3.2-3B-RewardModel.imatrix.gguf new file mode 100644 index 0000000..6901192 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49df624c024f06a2a5b4b487f120acdea7bf2a04f414b259ce65bcdb03422a25 +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..abaaab2 --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: NiuTrans/GRAM-LLaMA3.2-3B-RewardModel +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rewardmodel +- GRAM +- RLHF +- reward +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/NiuTrans/GRAM-LLaMA3.2-3B-RewardModel + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-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/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-i1-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.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. + +