commit b8d9ff95176be9e12b5c19c8976e8f2f81be186e Author: ModelHub XC Date: Mon Jun 1 02:55:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-optimized-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3e153ad --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-optimized.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-optimized.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-optimized.IQ4_XS.gguf b/Llama-3.2-3B-optimized.IQ4_XS.gguf new file mode 100644 index 0000000..1b9c35b --- /dev/null +++ b/Llama-3.2-3B-optimized.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8027a02c96b1e929a0b056d6d7d2fabbd3cf933774a4301741a361a6c3d25eb9 +size 1836338176 diff --git a/Llama-3.2-3B-optimized.Q2_K.gguf b/Llama-3.2-3B-optimized.Q2_K.gguf new file mode 100644 index 0000000..c1db39f --- /dev/null +++ b/Llama-3.2-3B-optimized.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73775fe675a5f437bda2df4f42d39f16ebaaf6f404b1fb54ea5b9c85e47f3d0 +size 1359367168 diff --git a/Llama-3.2-3B-optimized.Q3_K_L.gguf b/Llama-3.2-3B-optimized.Q3_K_L.gguf new file mode 100644 index 0000000..b786e59 --- /dev/null +++ b/Llama-3.2-3B-optimized.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7233f8fce5a3a05c6cbd0d525a1c99cc20ae37e8c314a1a1ede0dda582507e8 +size 1810779136 diff --git a/Llama-3.2-3B-optimized.Q3_K_M.gguf b/Llama-3.2-3B-optimized.Q3_K_M.gguf new file mode 100644 index 0000000..b50346e --- /dev/null +++ b/Llama-3.2-3B-optimized.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e2255343ba9e4cbb05c3aa95951aba95e87d3468aa189ebe821eef024f5b7b +size 1682590720 diff --git a/Llama-3.2-3B-optimized.Q3_K_S.gguf b/Llama-3.2-3B-optimized.Q3_K_S.gguf new file mode 100644 index 0000000..7d0e1eb --- /dev/null +++ b/Llama-3.2-3B-optimized.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd638bd8b1755cf51c02295591f12a12b055dd367d9aa51dc733aea590bfafb +size 1538280448 diff --git a/Llama-3.2-3B-optimized.Q4_K_M.gguf b/Llama-3.2-3B-optimized.Q4_K_M.gguf new file mode 100644 index 0000000..ec0ca44 --- /dev/null +++ b/Llama-3.2-3B-optimized.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cd39bbee5e21f2c41d26ae31d4aefbef8f257abc24b3700698659a38c569a6 +size 2014809088 diff --git a/Llama-3.2-3B-optimized.Q4_K_S.gguf b/Llama-3.2-3B-optimized.Q4_K_S.gguf new file mode 100644 index 0000000..966c86a --- /dev/null +++ b/Llama-3.2-3B-optimized.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a23864d0a41422faabd59f15c4f8f950b909e0517d3ee03ac5614844ae48c3 +size 1923632128 diff --git a/Llama-3.2-3B-optimized.Q5_K_M.gguf b/Llama-3.2-3B-optimized.Q5_K_M.gguf new file mode 100644 index 0000000..1c5f5c5 --- /dev/null +++ b/Llama-3.2-3B-optimized.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0ab23ddffd5df5296455e3adbe300d80a174eb08d482a990849755b374d9ff +size 2317585408 diff --git a/Llama-3.2-3B-optimized.Q5_K_S.gguf b/Llama-3.2-3B-optimized.Q5_K_S.gguf new file mode 100644 index 0000000..b692d8b --- /dev/null +++ b/Llama-3.2-3B-optimized.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e3662a102e5ed6bb9ea0cb51f7eaa98f8f1227c5398237b49c112dc7b92aae +size 2264943616 diff --git a/Llama-3.2-3B-optimized.Q6_K.gguf b/Llama-3.2-3B-optimized.Q6_K.gguf new file mode 100644 index 0000000..7831798 --- /dev/null +++ b/Llama-3.2-3B-optimized.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b9f523439b0f005c3f7abeed04a5b8c360c292b28161ccbfbba75c8ad3c24a +size 2639285248 diff --git a/Llama-3.2-3B-optimized.Q8_0.gguf b/Llama-3.2-3B-optimized.Q8_0.gguf new file mode 100644 index 0000000..2c8a801 --- /dev/null +++ b/Llama-3.2-3B-optimized.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3166b08ca9f58266a8fdc66d790f632f3a05931490afb8b8510c44c3703c68 +size 3417330688 diff --git a/Llama-3.2-3B-optimized.f16.gguf b/Llama-3.2-3B-optimized.f16.gguf new file mode 100644 index 0000000..a65f445 --- /dev/null +++ b/Llama-3.2-3B-optimized.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ff3468f697d2aa4f55cf4391ae20102f020a8b8b6399d1cff767684c3d9f2d +size 6429119488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5dc5271 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: fraQtl/Llama-3.2-3B-fraQtl-kv +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fraqtl +- kv-cache-optimized +- inference +--- +## About + + + + + + + + + +static quants of https://huggingface.co/fraQtl/Llama-3.2-3B-fraQtl-kv + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-optimized-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-i1-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-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-optimized-GGUF/resolve/main/Llama-3.2-3B-optimized.f16.gguf) | f16 | 6.5 | 16 bpw, overkill | + +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. + +