commit 5a0a0efee29df4893c2090f76728442d6434ef26 Author: ModelHub XC Date: Sat May 9 05:10:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6234948 --- /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 +Llama3.2-ColdBrew-3B-OverThinker.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-ColdBrew-3B-OverThinker.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-ColdBrew-3B-OverThinker.IQ4_XS.gguf b/Llama3.2-ColdBrew-3B-OverThinker.IQ4_XS.gguf new file mode 100644 index 0000000..891a7dd --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ca42ff910f47a662d76276fbe39239b0bccd50445a7e8b14d647e82b022771 +size 1840908096 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q2_K.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q2_K.gguf new file mode 100644 index 0000000..71367de --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0afab9214e8270ee142fffc3f9134bfd6ea313f063f1cf7be6257af589668f +size 1363937088 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_L.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_L.gguf new file mode 100644 index 0000000..123f7e5 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d393d009a4cea499dffb82f132cb18334eae757e0977377f9e380357261031fb +size 1815349056 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_M.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_M.gguf new file mode 100644 index 0000000..558124e --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a1ce3e1a0b3ab6f61ce11d59cc9971e45dd31d6bb3c9098229178e456e910f +size 1687160640 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_S.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_S.gguf new file mode 100644 index 0000000..78ee422 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b50829c7f299b4fc4cc43aaf180b0f958f665c7562455b108a316cd70135d8 +size 1542850368 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_M.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_M.gguf new file mode 100644 index 0000000..2f6f78d --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747dfeaa73afe9cb97aa3b6a1b46b34297367b642e408004f8d8ff3176539963 +size 2019379008 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_S.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_S.gguf new file mode 100644 index 0000000..f3e3239 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f6832b293bbc7cdb59dc7043eecb5df902b7036c3501aad805c1cf17d73548 +size 1928202048 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_M.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_M.gguf new file mode 100644 index 0000000..6231541 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36d27c305e1eaaccc6d06e964e2a18d80bc90c0515a402b000bc7828186babf +size 2322155328 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_S.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_S.gguf new file mode 100644 index 0000000..87f357e --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7becabb7227e0e4c8d602207e79407461bf464307060f8dd7a6b8dca55a18f2 +size 2269513536 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q6_K.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q6_K.gguf new file mode 100644 index 0000000..2166c25 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bdd5e25e02a5185568e1aa1a9d79800593c267152f3c44a116ed5c25df762b +size 2643855168 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.Q8_0.gguf b/Llama3.2-ColdBrew-3B-OverThinker.Q8_0.gguf new file mode 100644 index 0000000..ee5e07f --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da116c257804608d5fd5e9edcf10cc24db675af2f4e25c829c35afdffc698dc5 +size 3421900608 diff --git a/Llama3.2-ColdBrew-3B-OverThinker.f16.gguf b/Llama3.2-ColdBrew-3B-OverThinker.f16.gguf new file mode 100644 index 0000000..d4b7ef6 --- /dev/null +++ b/Llama3.2-ColdBrew-3B-OverThinker.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90e771b9724070b8356bf0a9dc7c39f9ab8bc796534d5202a3ac6d28bd6ddab +size 6433689408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b09b85e --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: SvalTek/Llama3.2-ColdBrew-3B-OverThinker +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SvalTek/Llama3.2-ColdBrew-3B-OverThinker + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-ColdBrew-3B-OverThinker-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/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-ColdBrew-3B-OverThinker-GGUF/resolve/main/Llama3.2-ColdBrew-3B-OverThinker.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. + +