commit bd715953c5709a907c9e6f89ef3e8454028e6f6e Author: ModelHub XC Date: Mon Oct 12 03:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..61e0645 --- /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 +Llama-3.2-SUN-2.5B-chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ1_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..229a8e4 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9881c0d7e0f0614b34202f8ad74cc80a63c6ea34a217c0affd99f31263368b46 +size 724998464 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ1_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..152ed02 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049bc91be18465813997e452f19dcdd228b2247e27aa33159cd36d12512dd207 +size 684890432 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ2_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..cad8ccf --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181b1483c35711b8014b928ee411a6f2ac96056f959faec31b4a14708e34ad3c +size 955362848 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ2_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..1153260 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f40ebf728562954ed3e45a6f93bc1a27bb0d31eca0ed34d12933c1558f7bd22 +size 901885472 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XS.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..751ab60 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cad87c6f81c9a3456478908f4e79f0694b3f129783d7a21d4890226a41a09dc +size 849516864 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XXS.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6744383 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45ad173b0ce526378ea5828c78f46153680639c4796a7916d1699b0d157335e +size 791845184 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ3_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..0480008 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b387e0cccd5daa54a058ba48c61a888fa9f8f7d55a1d2c05ee143b63d4538d8f +size 1204159616 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ3_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..4c241d8 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aea4a7e7bf17756ad9fac51b4f969d900223a8b4a540c403d82db1554a48ce1 +size 1177420928 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XS.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0a23a1f --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ddcdb98ebda5e4072f936339d2955abd245020d917680f28e1421e32260105 +size 1131807872 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XXS.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..82f99a4 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e7c4c22ebce9683b4c0652155984d45b95a532e0cf62e046ef02c534bfb79c +size 1048686112 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-IQ4_XS.gguf b/Llama-3.2-SUN-2.5B-chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..39a0821 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ade1c43822e7d897969805aa08de1d39b9c2cbf00e616185bb306d40e25df18 +size 1402542432 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q2_K.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q2_K.gguf new file mode 100644 index 0000000..6771d83 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e991d79655f611696a57afb343bf01abbf06c6b1ecbde332391fd8be3c9187e +size 1024651168 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_L.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..040e338 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a005b583b8b5719ed45c256b5ea3b8d586d65eb7c5cf3fa7fa64bd748b99ebf +size 1354630272 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..aa5129a --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe109db1f43470b4ccecfc47b69f7ef82c6fea052ec28f559455eaa99784748 +size 1271006336 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e9f8122 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ebf4558b2e67aa43bf82331bb8beab792b69391fb731ab5ce7a5e2c3285bab +size 1172964480 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_0.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0.gguf new file mode 100644 index 0000000..db5b5e9 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690727a36e382550a8d4e319af6622ff2727263ff91931daf09b28e49c68c8fa +size 1470520032 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_4.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..c11d471 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e07f7859e00d4171c64a8220855b8813631fa1ea38cfe1e52706de858fc5a6 +size 1466325728 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_8.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..7a7a7de --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0092904fe06f3ed3842290a978dbeed161fc24baca06fb148c69d943b17062a8 +size 1466325728 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_8_8.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..15414e2 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed87d8abbfcc3e1e4b0c8d94caa97bb392c2ae429cdee43eae7e66cf0886ca3f +size 1466325728 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..113fe48 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66165d4d0b98d0d922296574357583f3367cb428368fca6ff15cb4fb9f079709 +size 1539857120 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b02b10d --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:904bc6b89a2cc9efe39b9241087d1fa52809e35d3dd3f383f26052423cab8288 +size 1475238624 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ee1b535 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480227dc203a8c6f6cca5cffaf894f6d22811d509eed28c5f37b97b4a0ea337c +size 1780310240 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..cf84c94 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e86a4e392ad6cfacd2de735a4d082566ecfe0fb5a5aa6eff76268469099b16f +size 1742430432 diff --git a/Llama-3.2-SUN-2.5B-chat.i1-Q6_K.gguf b/Llama-3.2-SUN-2.5B-chat.i1-Q6_K.gguf new file mode 100644 index 0000000..8049afd --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a3ed89c0693ad30ceeef0d4956bd9cffc194285057af0fe61e37ea66715f37 +size 2035791680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d4b27d3 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: meditsolutions/Llama-3.2-SUN-2.5B-chat +datasets: +- argilla/OpenHermesPreferences +- argilla/magpie-ultra-v0.1 +- argilla/Capybara-Preferences-Filtered +- mlabonne/open-perfectblend +- HuggingFaceTB/everyday-conversations-llama3.1-2k +- WizardLMTeam/WizardLM_evol_instruct_V2_196k +- ProlificAI/social-reasoning-rlhf +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-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-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ1_M.gguf) | i1-IQ1_M | 0.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ2_S.gguf) | i1-IQ2_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ2_M.gguf) | i1-IQ2_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q2_K.gguf) | i1-Q2_K | 1.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ3_S.gguf) | i1-IQ3_S | 1.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ3_M.gguf) | i1-IQ3_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.6 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.6 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_0.gguf) | i1-Q4_0 | 1.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-i1-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.i1-Q6_K.gguf) | i1-Q6_K | 2.1 | 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..6cd97b5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42e17f293b6819fa2d235dad04a345bb9273991b854d9036830e388e26b4855 +size 2628861