commit fb321101dc389b4c58f32d5db34d06c3ec2e6c18 Author: ModelHub XC Date: Sat Sep 26 19:25:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dd08278 --- /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-3.2-3B-Instruct-roleplay-tuned.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_M.gguf new file mode 100644 index 0000000..878fade --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf96ba76cde195aa83f82a7878b1ead2ca52c3e388a5d5f4af3b7422b769552 +size 924192608 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_S.gguf new file mode 100644 index 0000000..4b6aab1 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c766edbd1b0f9d0e4b32b037113c0fea9bf77af00e4819aceea048d95a51db44 +size 868159328 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_M.gguf new file mode 100644 index 0000000..edcf171 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e144249f898e310038314281b0022bb5642e5c23ee62d58021c157645e465a7 +size 1229033312 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_S.gguf new file mode 100644 index 0000000..0c8a193 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5dbfdfdb48e0dd19373ab162b8c93b98387934b14d78e6370d14c32a1777cb7 +size 1154322272 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XS.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bae8bfb --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d511a1674cdefd645d591f399fe80646c8ca3541ec8b0cc6086a68423696d0 +size 1100549984 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..187742a --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:627e5e486a99d610232b480f68ef6f41f21410014258e6d3897bfdfa5e4c3707 +size 1017581408 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_M.gguf new file mode 100644 index 0000000..94caa5c --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9176dc7031d2e4e21046ba71c900169297158c5eee7436f90b4f2ee729e827f1 +size 1599670112 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_S.gguf new file mode 100644 index 0000000..a162194 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bcebaa86e6cb10d477aa9086cfc31d0528cb232e0525269d1d71c63adcf177 +size 1542850400 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XS.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e3a0b88 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab45a477057710916b4207cb51000e3455b2c5c93085530dfa7b7365bfbc948 +size 1476790112 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9b4b3b5 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df992e862ebd68efa8348fb7fae5b1f9f6e59d801dd0fc8efe7d4977d5e12ef +size 1348767584 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_NL.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a78ab74 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f5e2bf6017b737aa2804c43569baba48b1f49b7464f02e726d27436ff70fce +size 1917192032 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_XS.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_XS.gguf new file mode 100644 index 0000000..83bb157 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a471eb1b34ccb7d49a6992514ded06ebeea217a3ca31aa5915c7becb72c8031b +size 1829111648 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K.gguf new file mode 100644 index 0000000..cfaeb87 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8042a08e2173604d00342a0d04f663d6de01e89253d4e8adf6a8f237308b247 +size 1363937120 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K_S.gguf new file mode 100644 index 0000000..881a38e --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:001897a98a7bd88ff672a76c3db5449c196efd165492440c80a86873582d14ef +size 1274283872 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_L.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fd3fee0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee55560d431c23cdbf052f4bc8a3e8d6391b46e2741c041865d15880cd02305c +size 1815349088 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f04b08e --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babc1433e69c17c64592dbed6fd7092acfe9b33d7ad300687ab0cf0a3f3fbe84 +size 1687160672 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_S.gguf new file mode 100644 index 0000000..bf2c7bd --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ab97c396269cba5a321b22c9c31930a1d4163c0da15007495eef49a108b559d +size 1542850400 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_0.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_0.gguf new file mode 100644 index 0000000..fc397b3 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184733bcec40874ae5c931f5e35b1af8bdf963d98560a93c56421621251795a1 +size 1921910624 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_1.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_1.gguf new file mode 100644 index 0000000..59b5751 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9516e141df2b0b9e3a965aac0005b1dae396c8cefd22dfa661a90cd91dfc91c +size 2093352800 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_M.gguf new file mode 100644 index 0000000..59197e1 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f263aa7b308ed44a8a98a34a2fa90c89001b71f58d131b1aee6370dd1ff43a +size 2019379040 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e33d50e --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8409e8cfd8af9ba53c8a839909cd218492767ab7b8896f27c76a0bd151b580da +size 1928202080 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_M.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_M.gguf new file mode 100644 index 0000000..76f5493 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e979767a754aa56c15279268a7ee5093453ff97b784ef81837d7fc40b1aa3b0 +size 2322155360 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_S.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a0916fb --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b67673e7972aa551b18a6f33fdbcbe9f290c56953b2459cc5dcb260c0ceaa1 +size 2269513568 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q6_K.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q6_K.gguf new file mode 100644 index 0000000..8ea1cda --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65850536524685d5f7d3cbbb1008fb6c50107405fc0b1cc2c0b1df2c1b6fa10 +size 2643855200 diff --git a/Llama-3.2-3B-Instruct-roleplay-tuned.imatrix.gguf b/Llama-3.2-3B-Instruct-roleplay-tuned.imatrix.gguf new file mode 100644 index 0000000..6b6ad40 --- /dev/null +++ b/Llama-3.2-3B-Instruct-roleplay-tuned.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119ec7f752155e814e276ad14908e4771ca6c866158f08b372c069fd6a74560a +size 3012064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86782d7 --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: Indexnusrefather/Llama-3.2-3B-Instruct-roleplay-tuned +datasets: +- ChaoticNeutrals/Gryphes-Sonnet3.5-Charcard-Roleplay-Heavy_Filtering +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rp +- roleplay +- creative +- writer +- llama3.2 +- lora +- finetune +- experimental +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Indexnusrefather/Llama-3.2-3B-Instruct-roleplay-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-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-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-roleplay-tuned-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-roleplay-tuned.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. + +