commit dd8a256e33cc6e21b0dd6b8aee47bbf7ae779f63 Author: ModelHub XC Date: Sat Jul 11 09:00:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dc45096 --- /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 +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.IQ4_XS.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.IQ4_XS.gguf new file mode 100644 index 0000000..c35015e --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a5bdbe15b817e66caa89251b1cdb4e10688284f6ee20b0fbc1c79f68b0f8e5 +size 668620928 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q2_K.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q2_K.gguf new file mode 100644 index 0000000..80d1efc --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f5aea8b696fd23aebe34967d13ddfd60cd4aceed8f61dd745f06d47e44d216d +size 483399808 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_L.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_L.gguf new file mode 100644 index 0000000..e9d18e0 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffd8057f635eaec5db514d6e0025dea5f2c069164d291b6e6d42cde197b0f7a +size 635476096 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_M.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_M.gguf new file mode 100644 index 0000000..6dd6e31 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8781fbce74492c7ea7637b58dc0dd8f55c03eac0a5bde044fa9028c66f286dab +size 600348800 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_S.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_S.gguf new file mode 100644 index 0000000..c1cd293 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5b74c1dfe3cac80461f438bb1ea8f56b5a8f3d52daacc72562cc791c5fe2e7 +size 558160000 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_M.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_M.gguf new file mode 100644 index 0000000..b9d61bb --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eef9c1bacec2e62bbdeeb1b4027ba7e5463ff0216b649b21958a0bb086ebe21 +size 730896512 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_S.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_S.gguf new file mode 100644 index 0000000..1c304ed --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8815e8548d5af0153003178c7869a704224af6edc3277327701456c6da88b45e +size 700471424 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_M.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_M.gguf new file mode 100644 index 0000000..6b9fb6a --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae552038336fd94ae398717509b4e8e98b55002be2c78870f5f5190a6f5042e +size 843356288 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_S.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_S.gguf new file mode 100644 index 0000000..4e6c930 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1e8a52f0c847de9148280b8ad5c5b212f7ed3614fa2d60de876cc037280253 +size 825251968 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q6_K.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q6_K.gguf new file mode 100644 index 0000000..43e4211 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85deb862d54c4be52672652d5bede8e8515e356877ee71ccc7e0c9ac3fe73d38 +size 962844800 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q8_0.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q8_0.gguf new file mode 100644 index 0000000..4b3038d --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812340a8df3ce6a891448f4a2028a10a71f51da3f42a16e2ef670b9187722a60 +size 1246255232 diff --git a/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.f16.gguf b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.f16.gguf new file mode 100644 index 0000000..9301c42 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0d56aca3cc26d5353ba02b8d9d7d09f8ef6e4cff67fb808f8dd96ec3c6d299 +size 2343327872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b96723 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: DavidAU/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL +datasets: +- TeichAI/gemini-3-pro-preview-high-reasoning-1000x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- finetune +- All use cases +- bfloat16 +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- fiction writing +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- romance +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-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/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL-GGUF/resolve/main/LFM2.5-1.2B-Thinking-Gemini3-Pro1000-DISTILL.f16.gguf) | f16 | 2.4 | 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. + +