commit 88b3264283808a63cea95c6201510866c5fd65d9 Author: ModelHub XC Date: Mon Jun 15 21:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-NextGenmix-4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d67f36 --- /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-NextGenmix-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-NextGenmix-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-NextGenmix-4b.IQ4_XS.gguf b/Llama-NextGenmix-4b.IQ4_XS.gguf new file mode 100644 index 0000000..2a03685 --- /dev/null +++ b/Llama-NextGenmix-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a20f5ecfa7ca15afa0b3b23716b802eb0d089845706bb9a9d0323fe52bf93a2 +size 2268163360 diff --git a/Llama-NextGenmix-4b.Q2_K.gguf b/Llama-NextGenmix-4b.Q2_K.gguf new file mode 100644 index 0000000..a348d8f --- /dev/null +++ b/Llama-NextGenmix-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b1b6c52d25181bbe9a41abd49f2b42785b84028927cf512c1fc590698c5fc8 +size 1640774944 diff --git a/Llama-NextGenmix-4b.Q3_K_L.gguf b/Llama-NextGenmix-4b.Q3_K_L.gguf new file mode 100644 index 0000000..c65d239 --- /dev/null +++ b/Llama-NextGenmix-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738bc26da7816d8c82ebf9cc8cdd137cbb98df75a5477f04cc8698b0a97e7605 +size 2196690208 diff --git a/Llama-NextGenmix-4b.Q3_K_M.gguf b/Llama-NextGenmix-4b.Q3_K_M.gguf new file mode 100644 index 0000000..bfd60f6 --- /dev/null +++ b/Llama-NextGenmix-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:032e7ccc45c51717c05996502300d6cb259689298083ba6d99fe425ee778d7b2 +size 2052773152 diff --git a/Llama-NextGenmix-4b.Q3_K_S.gguf b/Llama-NextGenmix-4b.Q3_K_S.gguf new file mode 100644 index 0000000..ff59cb9 --- /dev/null +++ b/Llama-NextGenmix-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:171385f0ac5f608bd1bb4ca1da5df1c2388281dd23a197f81c82603589fc0702 +size 1885263136 diff --git a/Llama-NextGenmix-4b.Q4_K_M.gguf b/Llama-NextGenmix-4b.Q4_K_M.gguf new file mode 100644 index 0000000..7247684 --- /dev/null +++ b/Llama-NextGenmix-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c07a06517c7c9e19eb06da9469c949c419dbcc95d049637dd55d3136e846d6 +size 2482195744 diff --git a/Llama-NextGenmix-4b.Q4_K_S.gguf b/Llama-NextGenmix-4b.Q4_K_S.gguf new file mode 100644 index 0000000..6323ddb --- /dev/null +++ b/Llama-NextGenmix-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08a3ca4c27a4b4f41d8469739ba7dfa6ad6a0a6911e01a1480ab4a5daebdc8b +size 2379566368 diff --git a/Llama-NextGenmix-4b.Q5_K_M.gguf b/Llama-NextGenmix-4b.Q5_K_M.gguf new file mode 100644 index 0000000..2eaa4a7 --- /dev/null +++ b/Llama-NextGenmix-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3fff202a45692f9833d3400f2aff86d67c21cec7e0a5c97e8393e8a1794261 +size 2877476128 diff --git a/Llama-NextGenmix-4b.Q5_K_S.gguf b/Llama-NextGenmix-4b.Q5_K_S.gguf new file mode 100644 index 0000000..64e9827 --- /dev/null +++ b/Llama-NextGenmix-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8725420d6151b4760c6f3ba6fe3dbd03aad0d3502ef5740cee6abdf124d2c38 +size 2817314080 diff --git a/Llama-NextGenmix-4b.Q6_K.gguf b/Llama-NextGenmix-4b.Q6_K.gguf new file mode 100644 index 0000000..c9219c8 --- /dev/null +++ b/Llama-NextGenmix-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eeaa0f1364f1c0bbfddb8ab7d5fded3c9febbd12f7814ad0b48a016089205d7 +size 3297461536 diff --git a/Llama-NextGenmix-4b.Q8_0.gguf b/Llama-NextGenmix-4b.Q8_0.gguf new file mode 100644 index 0000000..5e54774 --- /dev/null +++ b/Llama-NextGenmix-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31db8d6c48bfdeecc72c8146134c53fd2fa50182bd0ef4ea7f69e564b70d6e93 +size 4268447008 diff --git a/Llama-NextGenmix-4b.f16.gguf b/Llama-NextGenmix-4b.f16.gguf new file mode 100644 index 0000000..8384cbf --- /dev/null +++ b/Llama-NextGenmix-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3794242347fd188e411b74df231ff34668c14ba4cce5fb2f4c20f4c49b1d09e2 +size 8027100448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ac019f8 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: powermove72/Llama-NextGenmix-4b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- chuanli11/Llama-3.2-3B-Instruct-uncensored +- bunnycore/Llama-3.2-3B-Mix +--- +## About + + + + + + +static quants of https://huggingface.co/powermove72/Llama-NextGenmix-4b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-NextGenmix-4b-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-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-NextGenmix-4b-GGUF/resolve/main/Llama-NextGenmix-4b.f16.gguf) | f16 | 8.1 | 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. + +