From 42465180d6e8cddc97155ecf1f8c04259c85afb5 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 3 Jun 2026 06:46:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/LFM2.5-350M-THINKING-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++ LFM2.5-350M-THINKING.IQ4_XS.gguf | 3 ++ LFM2.5-350M-THINKING.Q2_K.gguf | 3 ++ LFM2.5-350M-THINKING.Q3_K_L.gguf | 3 ++ LFM2.5-350M-THINKING.Q3_K_M.gguf | 3 ++ LFM2.5-350M-THINKING.Q3_K_S.gguf | 3 ++ LFM2.5-350M-THINKING.Q4_K_M.gguf | 3 ++ LFM2.5-350M-THINKING.Q4_K_S.gguf | 3 ++ LFM2.5-350M-THINKING.Q5_K_M.gguf | 3 ++ LFM2.5-350M-THINKING.Q5_K_S.gguf | 3 ++ LFM2.5-350M-THINKING.Q6_K.gguf | 3 ++ LFM2.5-350M-THINKING.Q8_0.gguf | 3 ++ LFM2.5-350M-THINKING.f16.gguf | 3 ++ README.md | 78 ++++++++++++++++++++++++++++++++ 14 files changed, 161 insertions(+) create mode 100644 .gitattributes create mode 100644 LFM2.5-350M-THINKING.IQ4_XS.gguf create mode 100644 LFM2.5-350M-THINKING.Q2_K.gguf create mode 100644 LFM2.5-350M-THINKING.Q3_K_L.gguf create mode 100644 LFM2.5-350M-THINKING.Q3_K_M.gguf create mode 100644 LFM2.5-350M-THINKING.Q3_K_S.gguf create mode 100644 LFM2.5-350M-THINKING.Q4_K_M.gguf create mode 100644 LFM2.5-350M-THINKING.Q4_K_S.gguf create mode 100644 LFM2.5-350M-THINKING.Q5_K_M.gguf create mode 100644 LFM2.5-350M-THINKING.Q5_K_S.gguf create mode 100644 LFM2.5-350M-THINKING.Q6_K.gguf create mode 100644 LFM2.5-350M-THINKING.Q8_0.gguf create mode 100644 LFM2.5-350M-THINKING.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9d92700 --- /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 +LFM2.5-350M-THINKING.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-350M-THINKING.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-350M-THINKING.IQ4_XS.gguf b/LFM2.5-350M-THINKING.IQ4_XS.gguf new file mode 100644 index 0000000..df80c7e --- /dev/null +++ b/LFM2.5-350M-THINKING.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7bae20798c275b03e2f5b70efdb4e365a076fd177c25afb4e8891e1aec1a140 +size 211804512 diff --git a/LFM2.5-350M-THINKING.Q2_K.gguf b/LFM2.5-350M-THINKING.Q2_K.gguf new file mode 100644 index 0000000..9f45439 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0257c7531a9d19d23f7bbb6daac4180f273ee345a0b029b08fbce72caf294dd9 +size 160596320 diff --git a/LFM2.5-350M-THINKING.Q3_K_L.gguf b/LFM2.5-350M-THINKING.Q3_K_L.gguf new file mode 100644 index 0000000..7739491 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66004f5e083f18734f22abc413f065d7ae7b018c243ec840891a1115f1e27361 +size 203047264 diff --git a/LFM2.5-350M-THINKING.Q3_K_M.gguf b/LFM2.5-350M-THINKING.Q3_K_M.gguf new file mode 100644 index 0000000..21e2fb1 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2669da326b6c62495d61434667dd6166536776b16f25a16ae253b26756575a44 +size 193151328 diff --git a/LFM2.5-350M-THINKING.Q3_K_S.gguf b/LFM2.5-350M-THINKING.Q3_K_S.gguf new file mode 100644 index 0000000..f6d27f3 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80c38209f3551a1b0a9fbe89d3a8bd46c6255e0244398c39d1079a9648dd719 +size 181150048 diff --git a/LFM2.5-350M-THINKING.Q4_K_M.gguf b/LFM2.5-350M-THINKING.Q4_K_M.gguf new file mode 100644 index 0000000..160c908 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dcad42efc8c52e7cf9654848ba2de78edd56113354d807b6e6f7c640545bedc +size 229310816 diff --git a/LFM2.5-350M-THINKING.Q4_K_S.gguf b/LFM2.5-350M-THINKING.Q4_K_S.gguf new file mode 100644 index 0000000..903599f --- /dev/null +++ b/LFM2.5-350M-THINKING.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80086002cbd6475a6782df9ca64b85be06aaf44495aef52d54bce2812fdb83c6 +size 220750176 diff --git a/LFM2.5-350M-THINKING.Q5_K_M.gguf b/LFM2.5-350M-THINKING.Q5_K_M.gguf new file mode 100644 index 0000000..689ca52 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c3aa82fc5155ddf9ec2f94b8f18bc68427d459936d55d079f4253815e8bdaf +size 260374880 diff --git a/LFM2.5-350M-THINKING.Q5_K_S.gguf b/LFM2.5-350M-THINKING.Q5_K_S.gguf new file mode 100644 index 0000000..1b28758 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3090200dee34bee19199fa541e3f71007ebd5fb4f097fe5f207e320c5fb5fb50 +size 255222112 diff --git a/LFM2.5-350M-THINKING.Q6_K.gguf b/LFM2.5-350M-THINKING.Q6_K.gguf new file mode 100644 index 0000000..805384b --- /dev/null +++ b/LFM2.5-350M-THINKING.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0acb4f29b643a193212ca12d350bc9570f34c24a2abb2248909d007bcb534f03 +size 293380448 diff --git a/LFM2.5-350M-THINKING.Q8_0.gguf b/LFM2.5-350M-THINKING.Q8_0.gguf new file mode 100644 index 0000000..d2e9f68 --- /dev/null +++ b/LFM2.5-350M-THINKING.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ea684dabeb153256697a4fa47d7585cdf9a062777d5599c58ab11814867003 +size 379216224 diff --git a/LFM2.5-350M-THINKING.f16.gguf b/LFM2.5-350M-THINKING.f16.gguf new file mode 100644 index 0000000..7f164aa --- /dev/null +++ b/LFM2.5-350M-THINKING.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3466baed9dc1f7a462c13402146b419e4d3e52ffc6aa869b31bbdd259cc43da3 +size 711483744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d41531d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: finnianx/LFM2.5-350M-THINKING +datasets: +- TeichAI/lordx64-claude-opus-4.7-max-cleaned +- Jackrong/DeepSeek-V4-Distill-8000x +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gguf +- llama.cpp +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/finnianx/LFM2.5-350M-THINKING + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-350M-THINKING-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/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-350M-THINKING-GGUF/resolve/main/LFM2.5-350M-THINKING.f16.gguf) | f16 | 0.8 | 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. + +