commit 086cd59680aae7cc7879931814922326f706dda5 Author: ModelHub XC Date: Thu Jul 16 20:48:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f09ee1 --- /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-thinking-v2-50k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2_3B-thinking-v2-50k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b60560c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: x1nx3r/llama-3.2_3B-thinking-v2-50k +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/x1nx3r/llama-3.2_3B-thinking-v2-50k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2_3B-thinking-v2-50k-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2_3B-thinking-v2-50k-GGUF/resolve/main/llama-3.2_3B-thinking-v2-50k.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. + + diff --git a/llama-3.2_3B-thinking-v2-50k.IQ4_XS.gguf b/llama-3.2_3B-thinking-v2-50k.IQ4_XS.gguf new file mode 100644 index 0000000..ce11e71 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c887fcd6f4faa22137ac4274f4af0767daae0d75cbdcece39b76c100860a7023 +size 1840917088 diff --git a/llama-3.2_3B-thinking-v2-50k.Q2_K.gguf b/llama-3.2_3B-thinking-v2-50k.Q2_K.gguf new file mode 100644 index 0000000..0e7b5f3 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57c85a0799e8f82a5b4daf979f39801f99e55f28dfb54c38f74b14cc03bdc71 +size 1363946080 diff --git a/llama-3.2_3B-thinking-v2-50k.Q3_K_L.gguf b/llama-3.2_3B-thinking-v2-50k.Q3_K_L.gguf new file mode 100644 index 0000000..7bdd88d --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9366ca85a5ef76cd7748566e7664b75983a06edcf526e8509df6471398d143 +size 1815358048 diff --git a/llama-3.2_3B-thinking-v2-50k.Q3_K_M.gguf b/llama-3.2_3B-thinking-v2-50k.Q3_K_M.gguf new file mode 100644 index 0000000..dc65d95 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210ee40c7adac6b0fb8cc985ac3b3b9d316374625877dada4490c78607618a51 +size 1687169632 diff --git a/llama-3.2_3B-thinking-v2-50k.Q3_K_S.gguf b/llama-3.2_3B-thinking-v2-50k.Q3_K_S.gguf new file mode 100644 index 0000000..8f53ceb --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2214ea3ce731bf353e307078c9266c7201a129f27b6ac4358e2d445bee5a86f +size 1542859360 diff --git a/llama-3.2_3B-thinking-v2-50k.Q4_K_M.gguf b/llama-3.2_3B-thinking-v2-50k.Q4_K_M.gguf new file mode 100644 index 0000000..3d0e19c --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd313f0e640e6fcaf70c578e89da115b98508be20e3490b16acff52d5ae3a37 +size 2019388000 diff --git a/llama-3.2_3B-thinking-v2-50k.Q4_K_S.gguf b/llama-3.2_3B-thinking-v2-50k.Q4_K_S.gguf new file mode 100644 index 0000000..16f45fe --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bf2df4864b89f3b99cfc5ac5ca09a3f1653bb19206020c3d8ca07fc7e770fe +size 1928211040 diff --git a/llama-3.2_3B-thinking-v2-50k.Q5_K_M.gguf b/llama-3.2_3B-thinking-v2-50k.Q5_K_M.gguf new file mode 100644 index 0000000..dc6265d --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6bab0a49ee54d440274a00475c976c49028e3c4c041869b18b7308e9012464 +size 2322164320 diff --git a/llama-3.2_3B-thinking-v2-50k.Q5_K_S.gguf b/llama-3.2_3B-thinking-v2-50k.Q5_K_S.gguf new file mode 100644 index 0000000..4428a03 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7866777c27fe9cb0303e329af955ab417b6161c6b9b04097e6619eaf7e2042 +size 2269522528 diff --git a/llama-3.2_3B-thinking-v2-50k.Q6_K.gguf b/llama-3.2_3B-thinking-v2-50k.Q6_K.gguf new file mode 100644 index 0000000..ebdf6c1 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89478f4e09842c87be32ee5c8ac2e37ae10a5229c467fc7fded27312c7ac1df +size 2643864160 diff --git a/llama-3.2_3B-thinking-v2-50k.Q8_0.gguf b/llama-3.2_3B-thinking-v2-50k.Q8_0.gguf new file mode 100644 index 0000000..e321d3b --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b312c7f065970f27a704da00b51e982926014c7ed9efb91cf01fe5361acaea +size 3421912576 diff --git a/llama-3.2_3B-thinking-v2-50k.f16.gguf b/llama-3.2_3B-thinking-v2-50k.f16.gguf new file mode 100644 index 0000000..24089b7 --- /dev/null +++ b/llama-3.2_3B-thinking-v2-50k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ed0b6aff9393e51d2e2b4ca81c29d692df04b9a0cb732cc00008749b056424 +size 6433712896