commit 5ce4bb58b2a8310430b9dc869e9ef14d8784a971 Author: ModelHub XC Date: Fri Apr 10 21:45:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Stock-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a404da6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Stock.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Stock.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Stock.IQ4_XS.gguf b/Llama-3.2-3B-Stock.IQ4_XS.gguf new file mode 100644 index 0000000..1e7ca02 --- /dev/null +++ b/Llama-3.2-3B-Stock.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323113fd93ee6a908e9ccfd2c239944e85ef9f48fcce89fc2c63a0b5cb0ecd68 +size 1840904448 diff --git a/Llama-3.2-3B-Stock.Q2_K.gguf b/Llama-3.2-3B-Stock.Q2_K.gguf new file mode 100644 index 0000000..88588bc --- /dev/null +++ b/Llama-3.2-3B-Stock.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ad0e24c36b9bf8ae5589fc4367cabbcc2ca6b1085b9f15aa3d345eefd874dd +size 1363933440 diff --git a/Llama-3.2-3B-Stock.Q3_K_L.gguf b/Llama-3.2-3B-Stock.Q3_K_L.gguf new file mode 100644 index 0000000..958f56a --- /dev/null +++ b/Llama-3.2-3B-Stock.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e62714542af5bf42f6751151c362c46cf8478da9b420af6d95da1e7b4fa3531 +size 1815345408 diff --git a/Llama-3.2-3B-Stock.Q3_K_M.gguf b/Llama-3.2-3B-Stock.Q3_K_M.gguf new file mode 100644 index 0000000..db05b12 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535b1b29fdd4d1d8c1d4bd4b7dd50ed7c12ff00ebda31cc66316da83504f5bbb +size 1687156992 diff --git a/Llama-3.2-3B-Stock.Q3_K_S.gguf b/Llama-3.2-3B-Stock.Q3_K_S.gguf new file mode 100644 index 0000000..a463291 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b60f30de43388b5a76b8c614e186e28d788becf21e2d4c85d3ff24cb136ff27 +size 1542846720 diff --git a/Llama-3.2-3B-Stock.Q4_0_4_4.gguf b/Llama-3.2-3B-Stock.Q4_0_4_4.gguf new file mode 100644 index 0000000..0098bc5 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af8250820743c53ec9b12c54914288d8e1122d606a74dda6ef8f2dd76a68a8d0 +size 1917188352 diff --git a/Llama-3.2-3B-Stock.Q4_K_M.gguf b/Llama-3.2-3B-Stock.Q4_K_M.gguf new file mode 100644 index 0000000..2d8d910 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e01b6810e0a9a56954f849dcd785a2c0be2e046b371c3a28cad09a111c4b8a +size 2019375360 diff --git a/Llama-3.2-3B-Stock.Q4_K_S.gguf b/Llama-3.2-3B-Stock.Q4_K_S.gguf new file mode 100644 index 0000000..2ff487c --- /dev/null +++ b/Llama-3.2-3B-Stock.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c32c54a6edf85c7f2f236f3b289c85b4ad0714a422c0947d17a2a400115a166 +size 1928198400 diff --git a/Llama-3.2-3B-Stock.Q5_K_M.gguf b/Llama-3.2-3B-Stock.Q5_K_M.gguf new file mode 100644 index 0000000..e19f4b4 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc1bd65fe8b22ca7a3847b5e39559ffce081639364f4895baebf2eeec32f29e +size 2322151680 diff --git a/Llama-3.2-3B-Stock.Q5_K_S.gguf b/Llama-3.2-3B-Stock.Q5_K_S.gguf new file mode 100644 index 0000000..bd358cc --- /dev/null +++ b/Llama-3.2-3B-Stock.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917040157a8f1d6a23d7f610f9807e205cf70efac5ac67177a2bca350cc0770e +size 2269509888 diff --git a/Llama-3.2-3B-Stock.Q6_K.gguf b/Llama-3.2-3B-Stock.Q6_K.gguf new file mode 100644 index 0000000..fae8661 --- /dev/null +++ b/Llama-3.2-3B-Stock.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb6673b01a97efbe57e19f7e2a5947f0f360a88f8d2d49db534134d4aa64107 +size 2643851520 diff --git a/Llama-3.2-3B-Stock.Q8_0.gguf b/Llama-3.2-3B-Stock.Q8_0.gguf new file mode 100644 index 0000000..c80e89e --- /dev/null +++ b/Llama-3.2-3B-Stock.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f983e16ad0144c8c8936d0f434339f9217b4b91b9b68ffd608eeb5dcffd0cd4 +size 3421896960 diff --git a/Llama-3.2-3B-Stock.f16.gguf b/Llama-3.2-3B-Stock.f16.gguf new file mode 100644 index 0000000..6afb39e --- /dev/null +++ b/Llama-3.2-3B-Stock.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7abe19c55c1f69e1adc35617dd79f47dbcae4b8eae6e1a18ea958d45d2634ad +size 6433685760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6f8653f --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Stock +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Stock + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-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-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Stock-GGUF/resolve/main/Llama-3.2-3B-Stock.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. + +