commit 6ba43fad47a22ae77309df910cace42e0f6e4ea8 Author: ModelHub XC Date: Thu Jun 4 03:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4fc31ca --- /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-PLLuM-8B-chat-2412.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-chat-2412.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ1_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ1_M.gguf new file mode 100644 index 0000000..8252872 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d58b757e64032e786a32fb378369d9befc57a0e410ef08c8594fb6d976fb41d +size 2161982144 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ1_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ1_S.gguf new file mode 100644 index 0000000..019f0ca --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574ec4acf9da6c03dab5e54dd10dfd466c05f30ed5751df97e9c4d75c2e79864 +size 2019637952 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ2_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ2_M.gguf new file mode 100644 index 0000000..71ddd59 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ead3791592c7e0b44c74de7de9e0c77f2549c0b3d6d0456bb07a53930b33b8 +size 2948292096 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ2_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ2_S.gguf new file mode 100644 index 0000000..d6a78f5 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6936b185f5e8ce08b9d368426c0193e8b321bc9c1368a166b6109b8893708a27 +size 2758499840 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ2_XS.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ2_XS.gguf new file mode 100644 index 0000000..33a3a9f --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb87db55a9a1413c77e402928a3238b1b9fc446bef75c16f01687a3f35cfe38 +size 2605791936 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ2_XXS.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8935c25 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae7616f60cfbb0a59111c3264edffe0ec3b853099bb01871fd7f81f0bacfec7 +size 2399222464 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ3_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ3_M.gguf new file mode 100644 index 0000000..e8d229b --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ca777836a737619f825a0ec74f4685dcda80daa607a58d736fb001fc5f4031 +size 3784835648 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ3_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ3_S.gguf new file mode 100644 index 0000000..c59d29c --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe68aad43059896be85b7698e9109c336a77e98f9bd6f6ba9c7b08d724252950 +size 3682337344 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ3_XS.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ3_XS.gguf new file mode 100644 index 0000000..555c8be --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9293bc2e712841c279579b2d643cfdf8e12fd47e6e8abf9c6483d5b4ede12c1 +size 3518759488 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ3_XXS.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..20ac015 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68b9f37baeee0496bb8a918daeba67b81454d86a77d4d9569361f56ab118351 +size 3274923520 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ4_NL.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a22db63 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335e3421ea76b746283d533c29d2c986315e495dc73ebf3a462bedbb19adac1c +size 4678002304 diff --git a/Llama-PLLuM-8B-chat-2412.i1-IQ4_XS.gguf b/Llama-PLLuM-8B-chat-2412.i1-IQ4_XS.gguf new file mode 100644 index 0000000..09dceb2 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64fcd33fb6c0c0fa882741850610cc297f69039f4cb16ce15298cab3d0a5f62c +size 4447675776 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q2_K.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q2_K.gguf new file mode 100644 index 0000000..0853227 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2568f9547f9fc450eb1fcac4fadb535f05544d866165b0bab0bef76083da9f +size 3179142912 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q2_K_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f9028da --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ea2e6e9f04c1068b71faaee0833d2264273a1e99c87fa9c888b7c24e720955 +size 2988826368 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q3_K_L.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1bf1495 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5100b5f77f8a254bdea1e1df57761f908fe12d9a39d25f6a02dae1c5931d317a +size 4321968704 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q3_K_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_M.gguf new file mode 100644 index 0000000..73f394b --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04829e9e277843395c29bc400d3aa206292eb4efb61a4b9a86bedc252256233 +size 4018930240 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q3_K_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a7226a0 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c077d7503fa4aaf6a76baecdfb95115e1204933cdbd0cbd673b80c8b0a2c06f +size 3664511552 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q4_0.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q4_0.gguf new file mode 100644 index 0000000..4c94aa3 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5b4632561decfb8dee27e0b5e976a90b2f9ebfa5eeff166b432d479136e4eb +size 4675905152 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q4_1.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q4_1.gguf new file mode 100644 index 0000000..7096cf8 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9e1ca9633180ec17d8e582ec5d1fd17cad2a04c11c19b4225fad584ba69d4d +size 5130266752 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q4_K_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q4_K_M.gguf new file mode 100644 index 0000000..39d4a96 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988d09e0115f5e320691be22c29d73514c30dcaaaaf85b38a06ed0fc969d6f3f +size 4920747648 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q4_K_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q4_K_S.gguf new file mode 100644 index 0000000..41509aa --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dc09126afae84b0f5429c9b987fed23e3c71a3d6adacd34787f3c83fbe5164 +size 4692682368 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q5_K_M.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q5_K_M.gguf new file mode 100644 index 0000000..09e629c --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da42135dc6514cddf2f0e12c643568bad6dc714914bd36e796a13e6327e5a9b +size 5733001856 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q5_K_S.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q5_K_S.gguf new file mode 100644 index 0000000..26979ef --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c624f9c4201c692d43d4f07bcd1141823811cd197abc0e3a2938a49a0968fb3 +size 5599308416 diff --git a/Llama-PLLuM-8B-chat-2412.i1-Q6_K.gguf b/Llama-PLLuM-8B-chat-2412.i1-Q6_K.gguf new file mode 100644 index 0000000..dc3a5c3 --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f29dac95088d6dd2530c3859eaacfca0c23ba0e6b145e85e4c8b3d514a47d05 +size 6596021952 diff --git a/Llama-PLLuM-8B-chat-2412.imatrix.gguf b/Llama-PLLuM-8B-chat-2412.imatrix.gguf new file mode 100644 index 0000000..b9668da --- /dev/null +++ b/Llama-PLLuM-8B-chat-2412.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a07ba516c1ec4d1a2c39d5ce7daf67c5804cff497af8ac1bcfab6d818dfc0eb +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..752bcbf --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: CYFRAGOVPL/Llama-PLLuM-8B-chat-2412 +language: +- pl +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-chat-2412 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-PLLuM-8B-chat-2412-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-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-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-chat-2412-i1-GGUF/resolve/main/Llama-PLLuM-8B-chat-2412.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. + +