commit 509f5673392ceca280d777fa3d781b556c3d1c60 Author: ModelHub XC Date: Sun Sep 13 20:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mixtral_Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ba4686 --- /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 +Mixtral_Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mixtral_Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mixtral_Chat.IQ4_XS.gguf b/Mixtral_Chat.IQ4_XS.gguf new file mode 100644 index 0000000..94eb45b --- /dev/null +++ b/Mixtral_Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c00ca32574172d2b96d2a13e6b3dd7ae7805aa3613bf3afdb4438a03b97f5e2 +size 3944389088 diff --git a/Mixtral_Chat.Q2_K.gguf b/Mixtral_Chat.Q2_K.gguf new file mode 100644 index 0000000..1a23aae --- /dev/null +++ b/Mixtral_Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea27c837c0cf4a0222ad7a447425c2b6f55451658226ab883b54165af1ea916 +size 2719242720 diff --git a/Mixtral_Chat.Q3_K_L.gguf b/Mixtral_Chat.Q3_K_L.gguf new file mode 100644 index 0000000..2b38a8f --- /dev/null +++ b/Mixtral_Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3182c2ffa6da475fbfee11cf5575f12c472ab9fb83e5abbada07422b73299ef4 +size 3822025184 diff --git a/Mixtral_Chat.Q3_K_M.gguf b/Mixtral_Chat.Q3_K_M.gguf new file mode 100644 index 0000000..74d7935 --- /dev/null +++ b/Mixtral_Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7381b1c3a806b4700d85351b286bb2b824ec86b9c3d800103de0d0e8f9fc95dd +size 3518986720 diff --git a/Mixtral_Chat.Q3_K_S.gguf b/Mixtral_Chat.Q3_K_S.gguf new file mode 100644 index 0000000..d894036 --- /dev/null +++ b/Mixtral_Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad5aed919ef320350cb4e61520a397fcec0122dad0ac002ceae69d4a3e61f22 +size 3164568032 diff --git a/Mixtral_Chat.Q4_K_M.gguf b/Mixtral_Chat.Q4_K_M.gguf new file mode 100644 index 0000000..09f83dc --- /dev/null +++ b/Mixtral_Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60a552d440d3362d48b7a1a61a708b9adae10a7ddc6ba1ac290d7d41a2f8af2 +size 4368439776 diff --git a/Mixtral_Chat.Q4_K_S.gguf b/Mixtral_Chat.Q4_K_S.gguf new file mode 100644 index 0000000..f3de4ea --- /dev/null +++ b/Mixtral_Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37375145a4e45bf58422b226007818ecc7f957fe334f816d5dd51f30832c6117 +size 4140374496 diff --git a/Mixtral_Chat.Q5_K_M.gguf b/Mixtral_Chat.Q5_K_M.gguf new file mode 100644 index 0000000..24d07ae --- /dev/null +++ b/Mixtral_Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b52f9d42b543c0e8be5746132af7b5f56abf4d94ec4dcf7c117f158b2c95a1 +size 5131409888 diff --git a/Mixtral_Chat.Q5_K_S.gguf b/Mixtral_Chat.Q5_K_S.gguf new file mode 100644 index 0000000..3c3f2af --- /dev/null +++ b/Mixtral_Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b8e47e8e8e6d1bc22fc1c9717bafde7f121638a3940203d1b0afcfd82be22c +size 4997716448 diff --git a/Mixtral_Chat.Q6_K.gguf b/Mixtral_Chat.Q6_K.gguf new file mode 100644 index 0000000..e1423df --- /dev/null +++ b/Mixtral_Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdec089e11dddb1d6413f497eaed187bd8eec20c4676d20a58fff669d709d87c +size 5942065632 diff --git a/Mixtral_Chat.Q8_0.gguf b/Mixtral_Chat.Q8_0.gguf new file mode 100644 index 0000000..632970d --- /dev/null +++ b/Mixtral_Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adcddcbe323c834b272c9041cd00f0e0014460805862fc8d8580a52fa696c19 +size 7695858144 diff --git a/Mixtral_Chat.f16.gguf b/Mixtral_Chat.f16.gguf new file mode 100644 index 0000000..50d7451 --- /dev/null +++ b/Mixtral_Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525bc82f6433a8f96bb600b643050f9b1a2ea9d411fbffc9aff79d91506962e4 +size 14484732384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1037612 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: LeroyDyer/Mixtral_Chat +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/LeroyDyer/Mixtral_Chat + + +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/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mixtral_Chat-GGUF/resolve/main/Mixtral_Chat.f16.gguf) | f16 | 14.6 | 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. + +