commit 62cbf567226e7e35b0dc8f129dbbe4bd4616a5a8 Author: ModelHub XC Date: Tue Sep 29 18:03:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-TitanFusion-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c2c3a0 --- /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-TitanFusion.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-TitanFusion.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-TitanFusion.IQ4_XS.gguf b/Llama-3.2-3B-TitanFusion.IQ4_XS.gguf new file mode 100644 index 0000000..8bf6874 --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fb1d33db6214335c9ff0ec38cc9ee33eecc14863bf1b3e349d58f8a211c254 +size 2050221760 diff --git a/Llama-3.2-3B-TitanFusion.Q2_K.gguf b/Llama-3.2-3B-TitanFusion.Q2_K.gguf new file mode 100644 index 0000000..5919f46 --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cd6d4436d62c4688842917d09ad7b8ed4fd12d2a09fd10523e0cef7f6c15b8 +size 1493219008 diff --git a/Llama-3.2-3B-TitanFusion.Q3_K_L.gguf b/Llama-3.2-3B-TitanFusion.Q3_K_L.gguf new file mode 100644 index 0000000..27f578e --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165aa3b3d9a4c983774a7eddeedba0d2a340bd3408886a343d2bfdc39b8de58b +size 1984646848 diff --git a/Llama-3.2-3B-TitanFusion.Q3_K_M.gguf b/Llama-3.2-3B-TitanFusion.Q3_K_M.gguf new file mode 100644 index 0000000..ead0b5e --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9670c39a28530a422607e53de401e7db1f309f9fabd34101ca35b83caca3a5f0 +size 1856458432 diff --git a/Llama-3.2-3B-TitanFusion.Q3_K_S.gguf b/Llama-3.2-3B-TitanFusion.Q3_K_S.gguf new file mode 100644 index 0000000..ddbceef --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffcfcdfaf215e6a11867d837171e88a4c8abdb0dafe5f5d2d856c2497fba423 +size 1712148160 diff --git a/Llama-3.2-3B-TitanFusion.Q4_K_M.gguf b/Llama-3.2-3B-TitanFusion.Q4_K_M.gguf new file mode 100644 index 0000000..d632780 --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d226f4157e03a95041a4d62a9a297cd269172b2311d9e22d375eee83ccc316a +size 2241005248 diff --git a/Llama-3.2-3B-TitanFusion.Q4_K_S.gguf b/Llama-3.2-3B-TitanFusion.Q4_K_S.gguf new file mode 100644 index 0000000..f56177d --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b03eefc84622440d8cc82ab448b19c094cc13130fbf26998e44b97bbac68f19 +size 2149828288 diff --git a/Llama-3.2-3B-TitanFusion.Q5_K_M.gguf b/Llama-3.2-3B-TitanFusion.Q5_K_M.gguf new file mode 100644 index 0000000..f040f7f --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc937a9f1457a5933f4467ece7130f8e29e9a186884a1c8f23374809fc32ea0e +size 2593031872 diff --git a/Llama-3.2-3B-TitanFusion.Q5_K_S.gguf b/Llama-3.2-3B-TitanFusion.Q5_K_S.gguf new file mode 100644 index 0000000..d492999 --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f76acaef4857fa0e45ba34d9508801da40b035880b5950006b3be9f012e8ea +size 2540390080 diff --git a/Llama-3.2-3B-TitanFusion.Q6_K.gguf b/Llama-3.2-3B-TitanFusion.Q6_K.gguf new file mode 100644 index 0000000..0bb7d6d --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e05432c09a9ebb7e77b029184f0e47dcf69d0ce3eafcc3b1fa766c9c1f331fa +size 2967060160 diff --git a/Llama-3.2-3B-TitanFusion.Q8_0.gguf b/Llama-3.2-3B-TitanFusion.Q8_0.gguf new file mode 100644 index 0000000..fe28b54 --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a806d0ffcd5ac11f52b8d8e95c844b2eb2be3303fe5e66d4ab81db3a2d4e017 +size 3840528064 diff --git a/Llama-3.2-3B-TitanFusion.f16.gguf b/Llama-3.2-3B-TitanFusion.f16.gguf new file mode 100644 index 0000000..058eb1f --- /dev/null +++ b/Llama-3.2-3B-TitanFusion.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05b5e798037370622663c239809f802c01bc8e57a2afd0b8ad87c91fa4606cb +size 7221694144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7f1aa1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-TitanFusion +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-TitanFusion + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-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-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-TitanFusion-GGUF/resolve/main/Llama-3.2-3B-TitanFusion.f16.gguf) | f16 | 7.3 | 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. + +