commit 4d5c342c53961b758c4b52ea5842d8cabb0fad3d Author: ModelHub XC Date: Mon May 25 06:14:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hathor-L3-8B-v.01-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e5df21 --- /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 +Hathor-L3-8B-v.01.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Hathor-L3-8B-v.01.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hathor-L3-8B-v.01.i1-IQ1_M.gguf b/Hathor-L3-8B-v.01.i1-IQ1_M.gguf new file mode 100644 index 0000000..9dbe324 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3e87c98ce29b1a7d75500627332e44cc4356551400c8797b1624f4a240f2b2 +size 2161972448 diff --git a/Hathor-L3-8B-v.01.i1-IQ1_S.gguf b/Hathor-L3-8B-v.01.i1-IQ1_S.gguf new file mode 100644 index 0000000..7d27f2c --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54702ff10fa0af8ee5a87919093d12b4e1c19e847d8156047b8f595fe68d41ef +size 2019628256 diff --git a/Hathor-L3-8B-v.01.i1-IQ2_M.gguf b/Hathor-L3-8B-v.01.i1-IQ2_M.gguf new file mode 100644 index 0000000..5d0507d --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e02f84ec68c21889c7febc8ae0cf429ea9f77f89925334eb83df02c6c2ab37 +size 2948281568 diff --git a/Hathor-L3-8B-v.01.i1-IQ2_S.gguf b/Hathor-L3-8B-v.01.i1-IQ2_S.gguf new file mode 100644 index 0000000..fee83cb --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:742ea028cd1c2b94921228a5ac2e3b0b4c7028725ec493aa354d43d4481285f3 +size 2758489312 diff --git a/Hathor-L3-8B-v.01.i1-IQ2_XS.gguf b/Hathor-L3-8B-v.01.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ed26356 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1eba3a3c0eae7ae6803014cec0ae60ecb965b8694046507cd359785425c74e +size 2605782240 diff --git a/Hathor-L3-8B-v.01.i1-IQ2_XXS.gguf b/Hathor-L3-8B-v.01.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..70e5a09 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656755931ecf6c8908461005d661dd2b6b6e7e98095bdb9f0fb00e17e3d82a0b +size 2399212768 diff --git a/Hathor-L3-8B-v.01.i1-IQ3_M.gguf b/Hathor-L3-8B-v.01.i1-IQ3_M.gguf new file mode 100644 index 0000000..15721af --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0591037be1b112430e78375646844e2754e424e55ab137f14231f7f9227bafff +size 3784824032 diff --git a/Hathor-L3-8B-v.01.i1-IQ3_S.gguf b/Hathor-L3-8B-v.01.i1-IQ3_S.gguf new file mode 100644 index 0000000..bbedb1b --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba79b60b27a815218911c7538532bffef18dcf97e26ba1e278223ad7f3169e6 +size 3682325728 diff --git a/Hathor-L3-8B-v.01.i1-IQ3_XS.gguf b/Hathor-L3-8B-v.01.i1-IQ3_XS.gguf new file mode 100644 index 0000000..432c402 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193b423d4e5c7df644b61db1a9d67ddf5eafb975dd2d272d75f5c46915ab224b +size 3518747872 diff --git a/Hathor-L3-8B-v.01.i1-IQ3_XXS.gguf b/Hathor-L3-8B-v.01.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d920431 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3cdc0db5c9de8579500bf329513ffdb1ef374d55f184efd78498422e80567c +size 3274912992 diff --git a/Hathor-L3-8B-v.01.i1-IQ4_XS.gguf b/Hathor-L3-8B-v.01.i1-IQ4_XS.gguf new file mode 100644 index 0000000..289d19f --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec05ed346f7de677e5154843e3d51c06358967b1191459eb175a8bf89ccd439d +size 4447663328 diff --git a/Hathor-L3-8B-v.01.i1-Q2_K.gguf b/Hathor-L3-8B-v.01.i1-Q2_K.gguf new file mode 100644 index 0000000..7529faf --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880646a873bb90d3f5a9871a04946a555dab664507b27dada4db019394f876e8 +size 3179132128 diff --git a/Hathor-L3-8B-v.01.i1-Q3_K_L.gguf b/Hathor-L3-8B-v.01.i1-Q3_K_L.gguf new file mode 100644 index 0000000..39ea9c4 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89d12507ba0a3be39695a96cabd04e04e87dc986627d6b2b6d402d59bfd86d4 +size 4321957088 diff --git a/Hathor-L3-8B-v.01.i1-Q3_K_M.gguf b/Hathor-L3-8B-v.01.i1-Q3_K_M.gguf new file mode 100644 index 0000000..01287a1 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0057ebd506ed2f3ea8e549df4587b889704afb529a20fefe5d12affffe91c9b +size 4018918624 diff --git a/Hathor-L3-8B-v.01.i1-Q3_K_S.gguf b/Hathor-L3-8B-v.01.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c462945 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b89cdadc7c6882bc5059f58a001774c551967cc38a4e998dc4f3eaab9cd1a3f +size 3664499936 diff --git a/Hathor-L3-8B-v.01.i1-Q4_0.gguf b/Hathor-L3-8B-v.01.i1-Q4_0.gguf new file mode 100644 index 0000000..c07c1bb --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598f69ed3d2f447956698a542939fea246bbe853da36c798a76c5c07acbeaa6b +size 4675892448 diff --git a/Hathor-L3-8B-v.01.i1-Q4_0_4_4.gguf b/Hathor-L3-8B-v.01.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..a0adc23 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b1f0bf0baaea93acf03bdd3f334a5c8f39abf07060ebd6fc63ade066bde75a +size 4661212384 diff --git a/Hathor-L3-8B-v.01.i1-Q4_0_4_8.gguf b/Hathor-L3-8B-v.01.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..2e1bcb4 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40850077230f0c01d3b2ef1e59072ece92437f7b1d4f89d9c6105f7ef62e6645 +size 4661212384 diff --git a/Hathor-L3-8B-v.01.i1-Q4_0_8_8.gguf b/Hathor-L3-8B-v.01.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..8510992 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e49fb00ce66e216287e1ecaa4c3cac1143111ebe79a6a9db6647bde4b94c6b +size 4661212384 diff --git a/Hathor-L3-8B-v.01.i1-Q4_K_M.gguf b/Hathor-L3-8B-v.01.i1-Q4_K_M.gguf new file mode 100644 index 0000000..569a28e --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a56f048ca9fd8508178b74124a024d2de5fb39b7788db3f81ad95ac7428ebf +size 4920734944 diff --git a/Hathor-L3-8B-v.01.i1-Q4_K_S.gguf b/Hathor-L3-8B-v.01.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fa8a757 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378d13f95711edfe5a5f4d12dc96792c8fc1a5b87f0c0a85e839596f6ec6cba3 +size 4692669664 diff --git a/Hathor-L3-8B-v.01.i1-Q5_K_M.gguf b/Hathor-L3-8B-v.01.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3ad05b2 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c890ef3bb871844ff843408f57038980718d6b8ec1f8ea2615e5d6a99703c052 +size 5732988128 diff --git a/Hathor-L3-8B-v.01.i1-Q5_K_S.gguf b/Hathor-L3-8B-v.01.i1-Q5_K_S.gguf new file mode 100644 index 0000000..29a296a --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e616243085bffa84a386b8ccaa4d3f18721a1df9495937ada193ad2e8dfe02 +size 5599294688 diff --git a/Hathor-L3-8B-v.01.i1-Q6_K.gguf b/Hathor-L3-8B-v.01.i1-Q6_K.gguf new file mode 100644 index 0000000..32bb156 --- /dev/null +++ b/Hathor-L3-8B-v.01.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7391fea9748c79a5206c037ed7d4ba5f656f37e62e53011fc3fc0a7706dfcccd +size 6596007136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..875ec6e --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ChaoticNeutrals/Hathor_RP-v.01-L3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hathor-L3-8B-v.01-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-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/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hathor-L3-8B-v.01-i1-GGUF/resolve/main/Hathor-L3-8B-v.01.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..004f6c5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7976bff9356220c5de7975f988a86634cf188c0196e7afe20cb301556ff3f77d +size 4988157