commit 07ad8719b444712e98780b08f1081d23003e0e0c Author: ModelHub XC Date: Mon Jun 15 06:17:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-krix-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fedb795 --- /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-krix-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-krix-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-krix-v2.IQ4_XS.gguf b/Llama-3.2-krix-v2.IQ4_XS.gguf new file mode 100644 index 0000000..9c382d7 --- /dev/null +++ b/Llama-3.2-krix-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0380d729d9061bfbc727a09dce0db100649744b0248959f70e43f17cd0ee5a15 +size 1840908224 diff --git a/Llama-3.2-krix-v2.Q2_K.gguf b/Llama-3.2-krix-v2.Q2_K.gguf new file mode 100644 index 0000000..ce7d102 --- /dev/null +++ b/Llama-3.2-krix-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:411b0bebeee20e313af0c9b5959307ca4309ff6ce6e33685eda5ae390aa0e474 +size 1363937216 diff --git a/Llama-3.2-krix-v2.Q3_K_L.gguf b/Llama-3.2-krix-v2.Q3_K_L.gguf new file mode 100644 index 0000000..8382be5 --- /dev/null +++ b/Llama-3.2-krix-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbc441f16b5706e65b9f4708d90bad2306807714d5a60fe8ccc6785afc6f140 +size 1815349184 diff --git a/Llama-3.2-krix-v2.Q3_K_M.gguf b/Llama-3.2-krix-v2.Q3_K_M.gguf new file mode 100644 index 0000000..09637aa --- /dev/null +++ b/Llama-3.2-krix-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a9ded16b95fe43da69bbd0c277eb27f75b0e47b885c2583e4504cc8494410e +size 1687160768 diff --git a/Llama-3.2-krix-v2.Q3_K_S.gguf b/Llama-3.2-krix-v2.Q3_K_S.gguf new file mode 100644 index 0000000..596e2e8 --- /dev/null +++ b/Llama-3.2-krix-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df92ecf6a1e6914adeb4f49baf385bbd8040519460d452b371610d75873dc4e6 +size 1542850496 diff --git a/Llama-3.2-krix-v2.Q4_K_M.gguf b/Llama-3.2-krix-v2.Q4_K_M.gguf new file mode 100644 index 0000000..36a2f67 --- /dev/null +++ b/Llama-3.2-krix-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e71675dcd75c5e841dbdeee8ffb8ad2b5f7b1c0821b7ab6de3c048c797dda3 +size 2019379136 diff --git a/Llama-3.2-krix-v2.Q4_K_S.gguf b/Llama-3.2-krix-v2.Q4_K_S.gguf new file mode 100644 index 0000000..853ee11 --- /dev/null +++ b/Llama-3.2-krix-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8216bee84a767f6240c7485240366b05a1364d2e6280dec11bfcfdcafde45f +size 1928202176 diff --git a/Llama-3.2-krix-v2.Q5_K_M.gguf b/Llama-3.2-krix-v2.Q5_K_M.gguf new file mode 100644 index 0000000..1b0f237 --- /dev/null +++ b/Llama-3.2-krix-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b45020d15ac978829536684b6a8e7b19036ebfeef1041617a00ad65f0efc14 +size 2322155456 diff --git a/Llama-3.2-krix-v2.Q5_K_S.gguf b/Llama-3.2-krix-v2.Q5_K_S.gguf new file mode 100644 index 0000000..fda2de4 --- /dev/null +++ b/Llama-3.2-krix-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02a11ac508466a89b74da10ec98e9b851fb9ddcc63976eb06f56edddd3436fa +size 2269513664 diff --git a/Llama-3.2-krix-v2.Q6_K.gguf b/Llama-3.2-krix-v2.Q6_K.gguf new file mode 100644 index 0000000..bdcaff6 --- /dev/null +++ b/Llama-3.2-krix-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a2e603b74947dbe88bbed549f23190b2b4cfb8fc9f0b2a8c44ea113cd5feed +size 2643855296 diff --git a/Llama-3.2-krix-v2.Q8_0.gguf b/Llama-3.2-krix-v2.Q8_0.gguf new file mode 100644 index 0000000..4dbf5b8 --- /dev/null +++ b/Llama-3.2-krix-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bcdcc1fd23d2b7fbeaea8f7ab889f24ee113fff00d0a832c0bae366e10f09a0 +size 3421900736 diff --git a/Llama-3.2-krix-v2.f16.gguf b/Llama-3.2-krix-v2.f16.gguf new file mode 100644 index 0000000..4ce77bd --- /dev/null +++ b/Llama-3.2-krix-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cead1648b10e5cc3d3debc9db504f2ff8b72b3c27030fe03234ce4a9d115381 +size 6433689536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3eceb4f --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Ali-Yaser/Llama-3.2-krix-v2 +datasets: +- arcee-ai/The-Tome +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- transformers +- unsloth +- llama +- vLLM +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Ali-Yaser/Llama-3.2-krix-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-krix-v2-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-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-krix-v2-GGUF/resolve/main/Llama-3.2-krix-v2.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. + +