commit 88a74a2eae2467d6126bee26639b3d141c357df5 Author: ModelHub XC Date: Thu Jul 2 06:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d11649d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_M.gguf new file mode 100644 index 0000000..6a58308 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6effaaf6d6aea20b2c21d77cfda9c7db6ab5000383a353a5987a3dbe1d50357e +size 4969721760 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_S.gguf new file mode 100644 index 0000000..6ac1cf9 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03907b01c61fe5789bd172286312c5beec2758b5864746141429ab2a24ca1558 +size 4476481440 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_M.gguf new file mode 100644 index 0000000..d10847d --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e4510b2db849cd02a86d1ab57099260f032d8c1dd0f4627769d367fe95cd636 +size 7168188320 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_S.gguf new file mode 100644 index 0000000..b4f8f12 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3b782e847140cb625dd77f64334a885f56c6b8021ff8435e59601125ee6a42 +size 6510534560 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XS.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6094756 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c659971701ae762bd034dc766f372b341fadf0c732190833e908266b510c4e41 +size 6455177120 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XXS.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..37c0d1a --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef61c6286028ba6a063474680cc8eac63324198ead3657bd1f59cb950880cf84 +size 5791788960 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_M.gguf new file mode 100644 index 0000000..593726a --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a36d3a6073383ca55697da315763d31e2a97d2617d886bf1b0e5f5942da5261 +size 9602625440 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_S.gguf new file mode 100644 index 0000000..3585792 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acec6d9bc63b69640167bd869848b919b1e7eff2f18fbaeafe76afdea6178a07 +size 9505140640 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XS.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3deb735 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b718215fdd2ee832ba6c8c38d4bdd6689f31afdd791b6340c6f7eba1bee7eea +size 8983883680 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XXS.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..07a81f0 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6244091c53f1d71f7a692389da00fcce55e7ca6b1f8a5801a8b7bee3e8597faa +size 8456093600 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ4_XS.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1ebe2aa --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e38a03a01f61e2f5182a333c482a807079ebdf1118337639359241dfed21b1c +size 11695292320 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K.gguf new file mode 100644 index 0000000..1e3fd39 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ad2c284e2729791d4794e83db5f16defad6c47459bf62d4eefb2ec9c7f8408 +size 8053067680 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K_S.gguf new file mode 100644 index 0000000..a4f30aa --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5e25db3b187f590a73ef39c2b336ed0e07539bde7c815aebe33878054d0344 +size 7448600480 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_L.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c5f3829 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a91c743edd0ab0d18f3ee6585c0c3f344b37c4e038f6b8606152821713bb186 +size 11371667360 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3fcafa5 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1c51ca7c896a12b075d4be132ceddb4ee9c8eea5f2116f82be48128fa8d053 +size 10468581280 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6e77ee1 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5482a4951a6ec1b1198ab540319555553c095f818621eb9b362b818727fc3edf +size 9500266400 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_0.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_0.gguf new file mode 100644 index 0000000..fc677b2 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02fe01a78233ad0470d72adfdbbea77c05bb2d9fb7d8dea20be4bfa9b1d611b +size 12397592480 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_1.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_1.gguf new file mode 100644 index 0000000..491ea0d --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f25003cf03e7a7aae7c77d70a53e2a5f5f7bac009986d51df2efa5b6be61838 +size 13710442400 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e0e225a --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd09ad734990a3dc9b32bb16f95c436409cf5644ebc9e57371046e75b9f1f2a2 +size 13245833120 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_S.gguf new file mode 100644 index 0000000..207ac40 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8f517b835bf57f5144a01bf8fc04abf0de2727e2040d6ea30de327767d8fb1 +size 12432654240 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_M.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_M.gguf new file mode 100644 index 0000000..31a7fbd --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5fdd8b667185fc43e5739db2d2371e33764a53bad710d98f9fcad91b1858fe +size 15512395680 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_S.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_S.gguf new file mode 100644 index 0000000..eb86e30 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e571822abbec2cd0b74bd4aa0a2fdd5160eb04c4028cf1df646f7edcfdea2bb +size 15057698720 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q6_K.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q6_K.gguf new file mode 100644 index 0000000..3161994 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:502a6a8dea085a17f4bcbdc525d32ef93bec91f4711644eddcc0825f4b9d677b +size 17920618400 diff --git a/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.imatrix.gguf b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.imatrix.gguf new file mode 100644 index 0000000..19582a6 --- /dev/null +++ b/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9999554ae3cf207f9ca0aa2a737058e70157810a3fb2f8de94693bf80cf9fa1 +size 48452192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..347bb95 --- /dev/null +++ b/README.md @@ -0,0 +1,113 @@ +--- +base_model: DavidAU/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking +datasets: +- TeichAI/glm-4.7-350x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mixture of experts +- moe +- 64 experts +- uncensored +- 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 + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/DavidAU/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-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/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_S.gguf) | i1-IQ1_S | 4.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ1_M.gguf) | i1-IQ1_M | 5.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_S.gguf) | i1-IQ2_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ2_M.gguf) | i1-IQ2_M | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q2_K.gguf) | i1-Q2_K | 8.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_S.gguf) | i1-IQ3_S | 9.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ3_M.gguf) | i1-IQ3_M | 9.7 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.8 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_0.gguf) | i1-Q4_0 | 12.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q4_1.gguf) | i1-Q4_1 | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.2 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.6 | | +| [GGUF](https://huggingface.co/mradermacher/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking-i1-GGUF/resolve/main/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking.i1-Q6_K.gguf) | i1-Q6_K | 18.0 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +