commit 7be4b1ad029ddb24df598e3f840848ae46e728c8 Author: ModelHub XC Date: Wed Jun 3 22:44:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-Queen-8B-A1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..abd4a54 --- /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 +LFM2.5-Queen-8B-A1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-Queen-8B-A1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-Queen-8B-A1B.IQ4_XS.gguf b/LFM2.5-Queen-8B-A1B.IQ4_XS.gguf new file mode 100644 index 0000000..3a63b61 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13c8eee18d1b58817d341de4064f481e1b2a90e19d29980f77653b7d775959c +size 4611239616 diff --git a/LFM2.5-Queen-8B-A1B.Q2_K.gguf b/LFM2.5-Queen-8B-A1B.Q2_K.gguf new file mode 100644 index 0000000..2fdb3e0 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a8becab8b5bd6924e0e7cb2ec52b17d82da37a685a5de412495648d71d2417 +size 3190435520 diff --git a/LFM2.5-Queen-8B-A1B.Q3_K_L.gguf b/LFM2.5-Queen-8B-A1B.Q3_K_L.gguf new file mode 100644 index 0000000..526ed0a --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4c9b5ce8c0581a6a525931c2826de2379917b555da195789922e435f0980c1 +size 4436864704 diff --git a/LFM2.5-Queen-8B-A1B.Q3_K_M.gguf b/LFM2.5-Queen-8B-A1B.Q3_K_M.gguf new file mode 100644 index 0000000..95aebaa --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de28097673de32123635cfb1d9bb5860de74fac8a2d0872cbb7a4a4e93ad953 +size 4108398272 diff --git a/LFM2.5-Queen-8B-A1B.Q3_K_S.gguf b/LFM2.5-Queen-8B-A1B.Q3_K_S.gguf new file mode 100644 index 0000000..d103900 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193af033892bc6308b3589161b15d199fa4da5c51e99133ff607c3b26d5839a9 +size 3755077312 diff --git a/LFM2.5-Queen-8B-A1B.Q4_K_M.gguf b/LFM2.5-Queen-8B-A1B.Q4_K_M.gguf new file mode 100644 index 0000000..397640f --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d3ef002e26e4dd80208a81691d9f06a15d76b0373cb9e7c9839af5c83556e0 +size 5155565248 diff --git a/LFM2.5-Queen-8B-A1B.Q4_K_S.gguf b/LFM2.5-Queen-8B-A1B.Q4_K_S.gguf new file mode 100644 index 0000000..286676a --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f21e12b2c31134fd93adf5cbef06abfa42077a91f9de18cbe792267cc0c1b3 +size 4863553216 diff --git a/LFM2.5-Queen-8B-A1B.Q5_K_M.gguf b/LFM2.5-Queen-8B-A1B.Q5_K_M.gguf new file mode 100644 index 0000000..f0832ab --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a29e2f3e598de04be919939a2eefa0d33e75a30e107a1ab32df8e1422969c2c +size 6030339776 diff --git a/LFM2.5-Queen-8B-A1B.Q5_K_S.gguf b/LFM2.5-Queen-8B-A1B.Q5_K_S.gguf new file mode 100644 index 0000000..535b314 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae5c2e0f53866f211cd2c65df29f4d3ed5d2b5cd353455df5e02c1a7d1c51ab3 +size 5870186176 diff --git a/LFM2.5-Queen-8B-A1B.Q6_K.gguf b/LFM2.5-Queen-8B-A1B.Q6_K.gguf new file mode 100644 index 0000000..c9c3d0f --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4af47cd3393a7a698fcebb3dac54bf8c555b0b37f8bb428d527d051d677ebfd +size 6959787712 diff --git a/LFM2.5-Queen-8B-A1B.Q8_0.gguf b/LFM2.5-Queen-8B-A1B.Q8_0.gguf new file mode 100644 index 0000000..4bfa8d2 --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48c8761c13d3b400a799348875a9d9c6f27508bf51e395b5abcf3ae8f3fd52e4 +size 9010196160 diff --git a/LFM2.5-Queen-8B-A1B.f16.gguf b/LFM2.5-Queen-8B-A1B.f16.gguf new file mode 100644 index 0000000..09ad06b --- /dev/null +++ b/LFM2.5-Queen-8B-A1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73fa3f934f7c9173c6272064a55b81887c82fab59c069b84049a0939d03084b +size 16947261120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c9e68cd --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: aifeifei798/LFM2.5-Queen-8B-A1B +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +- pt +library_name: transformers +license: other +license_link: LICENSE +license_name: lfm1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- liquid +- lfm2.5 +- edge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aifeifei798/LFM2.5-Queen-8B-A1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-Queen-8B-A1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-i1-GGUF +## 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/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q4_K_M.gguf) | Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q5_K_S.gguf) | Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q5_K_M.gguf) | Q5_K_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.Q8_0.gguf) | Q8_0 | 9.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-Queen-8B-A1B-GGUF/resolve/main/LFM2.5-Queen-8B-A1B.f16.gguf) | f16 | 17.0 | 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. + +