commit f8c363069ce2ebee14d2f7d22e57b4fea70b19fd Author: ModelHub XC Date: Sat Jun 6 18:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d74c47 --- /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 +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.f16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.IQ4_XS.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.IQ4_XS.gguf new file mode 100644 index 0000000..beee61e --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2bee016af75eb9fd69ca56cbb532e685759dd1fb6ec8fa75850d744c8bcdcb +size 4500455424 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q2_K.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q2_K.gguf new file mode 100644 index 0000000..8b72555 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c4dff3885b4ef1de2e3faee659e2a95b2e22d5ab0cb77c3774364a2c76c27c +size 3079651328 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_L.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_L.gguf new file mode 100644 index 0000000..95f3a01 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1899b214c515ae841ad8617d8bd96ed7fe5b3b3d58ad65cb0ffcc09c5dfd380c +size 4326080512 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_M.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_M.gguf new file mode 100644 index 0000000..febac48 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3693a1e49f2da5678168a9901a0e1eb49d1d8b600b68f9636c2018956b6f90 +size 3997614080 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_S.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_S.gguf new file mode 100644 index 0000000..8ed6c40 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6593214e460d8d2153a5facb7325aae841cbf1c53164047e1ddca50e4e3989da +size 3644293120 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_M.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_M.gguf new file mode 100644 index 0000000..cd34b9b --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f153dadc721f6aac0d3243130bf8dd653d38c39fb0c0753cf64f41e2be14bd +size 5044781056 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_S.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_S.gguf new file mode 100644 index 0000000..4b7e8e2 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c240a534fbc7e6044091523486169667616e0aefa5ca842701b17a6ef16dbd2b +size 4752769024 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_M.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_M.gguf new file mode 100644 index 0000000..c64845f --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36e82d12cba0a026fc293e3738b39379699f0e046dcb0029e5af66168a241338 +size 5919555584 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_S.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_S.gguf new file mode 100644 index 0000000..91a8ce9 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b91d3e728b58991a0398526828c2b2a15756c9b4c2fffbcf17c309254a4a342 +size 5759401984 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q6_K.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q6_K.gguf new file mode 100644 index 0000000..feff1b2 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:382f05cd21966da9d47b915247534b5fc537e7dc1a2d73bd452b48ac138d1f0f +size 6849003520 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q8_0.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q8_0.gguf new file mode 100644 index 0000000..1c56a0b --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb91f5bae6d58e2b89a4f6b73a26a4f604d8ea54db1412114d013854a3cfa28 +size 8868429824 diff --git a/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.f16.gguf b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.f16.gguf new file mode 100644 index 0000000..0b44c53 --- /dev/null +++ b/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4c8a4d2dbf7a52c0efad6deaf4d247aa3185ca9b92a9b161c6fdb83a6d6b68 +size 16685563904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea35bf7 --- /dev/null +++ b/README.md @@ -0,0 +1,107 @@ +--- +base_model: DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P +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/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-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/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_S.gguf) | Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q6_K.gguf) | Q6_K | 6.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.Q8_0.gguf) | Q8_0 | 9.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P-GGUF/resolve/main/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P.f16.gguf) | f16 | 16.8 | 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. + +