From 340eda49b5c8baecd4e32c130e6bd8f503b5bd76 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 1 Jun 2026 00:56:16 +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/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF Source: Original Platform --- .gitattributes | 46 ++++++++ ...Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf | 3 + ...7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf | 3 + ...Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf | 3 + ...7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf | 3 + ...7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf | 3 + README.md | 106 ++++++++++++++++++ 13 files changed, 185 insertions(+) create mode 100644 .gitattributes create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf create mode 100644 LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c37116 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf new file mode 100644 index 0000000..f7e6b42 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc60ae3d2a3a042ea91f8ccb6174cd37fe57c0803ac04ef1396f3fc4649c928 +size 6083173888 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf new file mode 100644 index 0000000..5a87419 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e75dc074b70e2f599554f9ce6763fc8732b8ac0ef07c9e1cc7bb78cc7cdfd1 +size 4143275520 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf new file mode 100644 index 0000000..8be7b40 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7252e23c878d6584e10c85fca803ff4e3f071c6114d0f1c2304e4d33f00f0f7 +size 5836758528 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf new file mode 100644 index 0000000..f59b7ee --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379b1882f78b1973cf7adf5f2193d18b1f8915c4ac7045ebd859ef89bb7b54a8 +size 5391375872 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf new file mode 100644 index 0000000..96c877a --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db7a44ab34df1d6c97de40cb74e3b603aa72e6baf334817fe9f469c4e2a51cd +size 4910046720 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf new file mode 100644 index 0000000..d18e4ca --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86815d44a95f181837263f854174ff1e00bc4e9a6cba733c2cc862371b96fc6 +size 6822682112 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf new file mode 100644 index 0000000..c348af4 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005ececfa36672541a7986e63afd7265a5a0e459b918528c9afd046c6df92c99 +size 6423698944 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf new file mode 100644 index 0000000..7ac2e30 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dcc2ee52b4ab6b449f49c912d0bca438761124b4eb9357e5fef5faedf02a9b +size 8006000128 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf new file mode 100644 index 0000000..6bc91a0 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2c865510a8b5af87ca488b14f12df60891184bf04ab2eb979f77bbfcf8b3b9 +size 7783177728 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf new file mode 100644 index 0000000..1194e11 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a393947a7dd31ee645547a928ae170cdc669fa041e62f92aed432c2d5fa26e9 +size 9263275520 diff --git a/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf new file mode 100644 index 0000000..f31c633 --- /dev/null +++ b/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772d7b9fe6ae40d47050402047742bbf6dc60c723a4007ad1886eb39ade773c1 +size 11994783232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aef79bb --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +base_model: DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finetune +- unsloth +- mixture of experts +- sparse moe +- moe +- heretic +- uncensored +- aliterated +- finetune +- unsloth +- finetune +- all use cases +- coder +- 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 +- roleplaying +- bfloat16 +- all use cases +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-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/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q2_K.gguf) | Q2_K | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_S.gguf) | Q3_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q3_K_L.gguf) | Q3_K_L | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.IQ4_XS.gguf) | IQ4_XS | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_S.gguf) | Q4_K_S | 6.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q4_K_M.gguf) | Q4_K_M | 6.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_S.gguf) | Q5_K_S | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q5_K_M.gguf) | Q5_K_M | 8.1 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q6_K.gguf) | Q6_K | 9.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2-GGUF/resolve/main/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2.Q8_0.gguf) | Q8_0 | 12.1 | fast, best quality | + +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. + +