commit 799dd9cd8f630e5e0c6f65fefe843dbfe6b9c143 Author: ModelHub XC Date: Sat Sep 26 20:07:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Poro-2-8B-base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07e2355 --- /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 +Llama-Poro-2-8B-base.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Poro-2-8B-base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Poro-2-8B-base.i1-IQ1_M.gguf b/Llama-Poro-2-8B-base.i1-IQ1_M.gguf new file mode 100644 index 0000000..d787bf4 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9baa771b7ef20094462bb69bbdb3a0e8c2e7f61b31d2760d94ec184a1e01d0 +size 2161973120 diff --git a/Llama-Poro-2-8B-base.i1-IQ1_S.gguf b/Llama-Poro-2-8B-base.i1-IQ1_S.gguf new file mode 100644 index 0000000..7783130 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f44ac820cb3d13d8db863b4abd38153f6e79742e7fb8d6b4e1307206f45f52 +size 2019628928 diff --git a/Llama-Poro-2-8B-base.i1-IQ2_M.gguf b/Llama-Poro-2-8B-base.i1-IQ2_M.gguf new file mode 100644 index 0000000..fb6fcbf --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c4845f1cdf5bcaca8c3da6cac9ece770409a14fe22bb0b1c924dbb5c657e63 +size 2948282240 diff --git a/Llama-Poro-2-8B-base.i1-IQ2_S.gguf b/Llama-Poro-2-8B-base.i1-IQ2_S.gguf new file mode 100644 index 0000000..2fad6dd --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d4d6d2f64b322096b30b901fcdad17dbdfaf951f61329f1523bd0d3fd980f9 +size 2758489984 diff --git a/Llama-Poro-2-8B-base.i1-IQ2_XS.gguf b/Llama-Poro-2-8B-base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a0bbac7 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d6c143da53e648e83b53f653e0fe514b34012ed4f8fece57e5f03d0602b40a +size 2605782912 diff --git a/Llama-Poro-2-8B-base.i1-IQ2_XXS.gguf b/Llama-Poro-2-8B-base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fd28192 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc0ce7604a3f290fe9b9ecb846c2925f1ed96a86ec720baf15a3d81841040c2 +size 2399213440 diff --git a/Llama-Poro-2-8B-base.i1-IQ3_M.gguf b/Llama-Poro-2-8B-base.i1-IQ3_M.gguf new file mode 100644 index 0000000..dfc1024 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91733da1be2079b03ea0c2e16d7c5c72a47ae270b000523fc08f0d6695808940 +size 3784824704 diff --git a/Llama-Poro-2-8B-base.i1-IQ3_S.gguf b/Llama-Poro-2-8B-base.i1-IQ3_S.gguf new file mode 100644 index 0000000..082c28c --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:411a51979fa5ee9b0690d8de8c72269dd5b4156045f2e52f6496a638cba392b9 +size 3682326400 diff --git a/Llama-Poro-2-8B-base.i1-IQ3_XS.gguf b/Llama-Poro-2-8B-base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2861322 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5556b122173534ff76836ab192c627eb80bca1099688ac88feaef3bb8a304abb +size 3518748544 diff --git a/Llama-Poro-2-8B-base.i1-IQ3_XXS.gguf b/Llama-Poro-2-8B-base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e0a0ed1 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5299143256abd89c4a37a195d3c8f0e23bd88b48ced453c70836fcf6b3baee +size 3274913664 diff --git a/Llama-Poro-2-8B-base.i1-IQ4_NL.gguf b/Llama-Poro-2-8B-base.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2e8aba2 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11acf68b8cc621c8e888c565c580a6fb3250b07cd05ed9d2931261fa1998dcbd +size 4677990272 diff --git a/Llama-Poro-2-8B-base.i1-IQ4_XS.gguf b/Llama-Poro-2-8B-base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1c4acc9 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc789091f10523b5e689837829b27b41f849fc0c55c3b7c98f4ed90fe58b294 +size 4447664000 diff --git a/Llama-Poro-2-8B-base.i1-Q2_K.gguf b/Llama-Poro-2-8B-base.i1-Q2_K.gguf new file mode 100644 index 0000000..3c0ab47 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40daff85388945a74fbb5805500c2c17a69b1c4c2658fe9e5ac60601e0b7961f +size 3179132800 diff --git a/Llama-Poro-2-8B-base.i1-Q2_K_S.gguf b/Llama-Poro-2-8B-base.i1-Q2_K_S.gguf new file mode 100644 index 0000000..a4d9707 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ddf0be4534676165c2b30a238ba06750d2d9eb050c6f905c4983ec1c512248e +size 2988816256 diff --git a/Llama-Poro-2-8B-base.i1-Q3_K_L.gguf b/Llama-Poro-2-8B-base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2450ca1 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d408fc679af2193327e75cfeaa17bbfe10203817c8cb79bc3a77de641a93485 +size 4321957760 diff --git a/Llama-Poro-2-8B-base.i1-Q3_K_M.gguf b/Llama-Poro-2-8B-base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4e8f7f8 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1019572138d59ce787518b513a9d9b21eeac6152769198055d0d14206655ca +size 4018919296 diff --git a/Llama-Poro-2-8B-base.i1-Q3_K_S.gguf b/Llama-Poro-2-8B-base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..877e294 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782ae0dd773861bcae814cac34421c5fbcb0e18974aeb31a15b7ff2558405731 +size 3664500608 diff --git a/Llama-Poro-2-8B-base.i1-Q4_0.gguf b/Llama-Poro-2-8B-base.i1-Q4_0.gguf new file mode 100644 index 0000000..1a2bc7e --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175c584796adba571bd326dcb851275d1f0d72b8c2a5f00b3e35077029f8a704 +size 4675893120 diff --git a/Llama-Poro-2-8B-base.i1-Q4_1.gguf b/Llama-Poro-2-8B-base.i1-Q4_1.gguf new file mode 100644 index 0000000..c957e5b --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190d81651bd3f6e2e1af6e0bc90c1899abec56c5001b48aaf24eeeb2cdb6cef4 +size 5130254208 diff --git a/Llama-Poro-2-8B-base.i1-Q4_K_M.gguf b/Llama-Poro-2-8B-base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8607880 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d695d3df0215a5033f27973887d435b9e7bbb103edc9df1459faae811527027 +size 4920735616 diff --git a/Llama-Poro-2-8B-base.i1-Q4_K_S.gguf b/Llama-Poro-2-8B-base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b877e9c --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47860e51eff4ecfce673e4f996e0abc2aa819700fd1625e8d03d795e21e3c5cb +size 4692670336 diff --git a/Llama-Poro-2-8B-base.i1-Q5_K_M.gguf b/Llama-Poro-2-8B-base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..88ab5e0 --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18bdc08eae1de46a96938e9ecddf7cd3c8528ed14146ca426f5d900c86c96190 +size 5732988800 diff --git a/Llama-Poro-2-8B-base.i1-Q5_K_S.gguf b/Llama-Poro-2-8B-base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..be766db --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f56b04057740c27173a17fee24b0f470e8c6bf27024950cc4fb5b5fef5b0d9f +size 5599295360 diff --git a/Llama-Poro-2-8B-base.i1-Q6_K.gguf b/Llama-Poro-2-8B-base.i1-Q6_K.gguf new file mode 100644 index 0000000..47f557e --- /dev/null +++ b/Llama-Poro-2-8B-base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efbf4ac7a3c90c0707ecbcc66bac0469e513752a73be3221474c7c83f28a7be +size 6596007808 diff --git a/Llama-Poro-2-8B-base.imatrix.gguf b/Llama-Poro-2-8B-base.imatrix.gguf new file mode 100644 index 0000000..67df422 --- /dev/null +++ b/Llama-Poro-2-8B-base.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd251de2554a3d82b59f51af3fac6edf9367c1c72d09b07c7f4275080e5f292 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ad00e5 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: LumiOpen/Llama-Poro-2-8B-base +datasets: +- HuggingFaceFW/fineweb-2 +- HuggingFaceFW/fineweb-edu +- bigcode/starcoderdata +- HuggingFaceTB/finemath +language: +- fi +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/LumiOpen/Llama-Poro-2-8B-base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-Poro-2-8B-base-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-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/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Poro-2-8B-base-i1-GGUF/resolve/main/Llama-Poro-2-8B-base.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. + +