commit b2572447276d629979e4406ec877e3d18699ca3d Author: ModelHub XC Date: Sun May 24 21:48:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniCPM4-MCP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..82f18f4 --- /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 +MiniCPM4-MCP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniCPM4-MCP.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniCPM4-MCP.IQ4_XS.gguf b/MiniCPM4-MCP.IQ4_XS.gguf new file mode 100644 index 0000000..5562db5 --- /dev/null +++ b/MiniCPM4-MCP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5ab3a670501dad5e7bf2dd214fced41fefca78b1e38342c516b8c4bc60e835 +size 4485190752 diff --git a/MiniCPM4-MCP.Q2_K.gguf b/MiniCPM4-MCP.Q2_K.gguf new file mode 100644 index 0000000..15ca1c2 --- /dev/null +++ b/MiniCPM4-MCP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb981d78ef7db24202bd38d7058d76ccbc5b891272761b1a9c8329ce673fefa +size 3117032032 diff --git a/MiniCPM4-MCP.Q3_K_L.gguf b/MiniCPM4-MCP.Q3_K_L.gguf new file mode 100644 index 0000000..d841e26 --- /dev/null +++ b/MiniCPM4-MCP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7fe94911ed0df533c47b0c55eaa2346f2247f22ae256264f7681bca4cca705 +size 4337982304 diff --git a/MiniCPM4-MCP.Q3_K_M.gguf b/MiniCPM4-MCP.Q3_K_M.gguf new file mode 100644 index 0000000..2205957 --- /dev/null +++ b/MiniCPM4-MCP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f266cbadb551c13db37a3da18d83e27dcafb30b7177f4c6905dd163acf10447c +size 4015283040 diff --git a/MiniCPM4-MCP.Q3_K_S.gguf b/MiniCPM4-MCP.Q3_K_S.gguf new file mode 100644 index 0000000..d9acd16 --- /dev/null +++ b/MiniCPM4-MCP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee794226f9744ad51e129c36f987f57ce1936c54b82ed77eb35ea789c66253c +size 3637271392 diff --git a/MiniCPM4-MCP.Q4_K_M.gguf b/MiniCPM4-MCP.Q4_K_M.gguf new file mode 100644 index 0000000..907ac99 --- /dev/null +++ b/MiniCPM4-MCP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85408790360db966edc35a0eaa74c480fc11df49cc281160cf8e9466d6a2e09f +size 4965533792 diff --git a/MiniCPM4-MCP.Q4_K_S.gguf b/MiniCPM4-MCP.Q4_K_S.gguf new file mode 100644 index 0000000..23c9fc8 --- /dev/null +++ b/MiniCPM4-MCP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b32ca9685bc94f713709e08aea2a0f7a604ade74c8547828efc8d089423de1cf +size 4718463072 diff --git a/MiniCPM4-MCP.Q5_K_M.gguf b/MiniCPM4-MCP.Q5_K_M.gguf new file mode 100644 index 0000000..a82d0d4 --- /dev/null +++ b/MiniCPM4-MCP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a404da411c11757560e558579e1f2266cc0561375d4fecc3a1adbf659e5446 +size 5814736992 diff --git a/MiniCPM4-MCP.Q5_K_S.gguf b/MiniCPM4-MCP.Q5_K_S.gguf new file mode 100644 index 0000000..96ac9a6 --- /dev/null +++ b/MiniCPM4-MCP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b6520255cd347d3fa8b6beb0ca013069c5cc397fe0ac39e10f6025cf3028cf8 +size 5669902432 diff --git a/MiniCPM4-MCP.Q6_K.gguf b/MiniCPM4-MCP.Q6_K.gguf new file mode 100644 index 0000000..d0d712a --- /dev/null +++ b/MiniCPM4-MCP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9f1d2dbe41558d02d594d1b584fe01ad53b3d5f93f828f209b8aad321619bf +size 6717015392 diff --git a/MiniCPM4-MCP.Q8_0.gguf b/MiniCPM4-MCP.Q8_0.gguf new file mode 100644 index 0000000..79437c8 --- /dev/null +++ b/MiniCPM4-MCP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26ad2bfea01717c1226f8806b87905a6780467e1d311ba6f9b415fe2bf3d668 +size 8699317088 diff --git a/MiniCPM4-MCP.f16.gguf b/MiniCPM4-MCP.f16.gguf new file mode 100644 index 0000000..25d6d71 --- /dev/null +++ b/MiniCPM4-MCP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9624f9867deaddfcc8d2758d9cd0d5ff5f3dd8e80cab81b5e595179e5e22897 +size 16372743008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a1b5a3 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: openbmb/MiniCPM4-MCP +language: +- zh +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/openbmb/MiniCPM4-MCP + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MiniCPM4-MCP-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/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiniCPM4-MCP-GGUF/resolve/main/MiniCPM4-MCP.f16.gguf) | f16 | 16.5 | 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. + +