commit b54beca01efb7b47ad8003bb79502b9e8e30b669 Author: ModelHub XC Date: Tue Jun 16 18:44:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-3.0-3b-a800m-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d93ac10 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +granite-3.0-3b-a800m-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-3b-a800m-instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0879208 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ibm-granite/granite-3.0-3b-a800m-instruct +language: +- en +library_name: transformers +license: apache-2.0 +no_imatrix: Missing importance matrix for tensor blk.0.ffn_gate_exps.weight in a very + low-bit quantization +quantized_by: mradermacher +tags: +- language +- granite-3.0 +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3.0-3b-a800m-instruct + + +## 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/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-3b-a800m-instruct-GGUF/resolve/main/granite-3.0-3b-a800m-instruct.f16.gguf) | f16 | 6.9 | 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. + + diff --git a/granite-3.0-3b-a800m-instruct.IQ4_XS.gguf b/granite-3.0-3b-a800m-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9752c5f --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae31570eeac79a789fdf9e289ba2b43cd88660f3cf6eee289107900ebdf2389 +size 1842989216 diff --git a/granite-3.0-3b-a800m-instruct.Q2_K.gguf b/granite-3.0-3b-a800m-instruct.Q2_K.gguf new file mode 100644 index 0000000..b390ac9 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b3fdb79f93f0a4e2ce9bbeefc8515876cb68605516b945e8feab42faacc1db +size 1266140416 diff --git a/granite-3.0-3b-a800m-instruct.Q3_K_L.gguf b/granite-3.0-3b-a800m-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..bc78aab --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7a705f6a3ac98f3bc8df8ad53ca70fb33b68e728ab50f3e1a84d1bd71f75ee +size 1773979328 diff --git a/granite-3.0-3b-a800m-instruct.Q3_K_M.gguf b/granite-3.0-3b-a800m-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..9545517 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57a9a2b3c402ba0237144004431cc5eb5861d4e86031606164352d83b5443d9 +size 1643628224 diff --git a/granite-3.0-3b-a800m-instruct.Q3_K_S.gguf b/granite-3.0-3b-a800m-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..0ccd803 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b34354f4a49683ad6935c9fef8213613839a2c0fd05a358ce4e0e83d7032d0e +size 1488504512 diff --git a/granite-3.0-3b-a800m-instruct.Q4_0_4_4.gguf b/granite-3.0-3b-a800m-instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..e7eb162 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839044b081df353845959ac2fd48773b4c38104b1473e945172545c394499a79 +size 1926351136 diff --git a/granite-3.0-3b-a800m-instruct.Q4_K_M.gguf b/granite-3.0-3b-a800m-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..2f31ffa --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a009f1fba722b87df93e5ea2828e0267fb292af3b200f67b59208c839504c986 +size 2059356448 diff --git a/granite-3.0-3b-a800m-instruct.Q4_K_S.gguf b/granite-3.0-3b-a800m-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..2ac26e2 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1e9d007206e2613de9cc3abc8b2f97f25a8c1fa45662b69b26638b182b21c9 +size 1942472992 diff --git a/granite-3.0-3b-a800m-instruct.Q5_K_M.gguf b/granite-3.0-3b-a800m-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..5883ad8 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fa89d71a8fbf0d7dc8fc62f603ac04e35ee6baa92025975e4e24876fc3872d +size 2406959968 diff --git a/granite-3.0-3b-a800m-instruct.Q5_K_S.gguf b/granite-3.0-3b-a800m-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..758db69 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbf52fdc3e12babea5f9526f7142bb51823b67f68ea4fc638e7654e10612f10 +size 2338442080 diff --git a/granite-3.0-3b-a800m-instruct.Q6_K.gguf b/granite-3.0-3b-a800m-instruct.Q6_K.gguf new file mode 100644 index 0000000..b8b9293 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b0c65f5c172bc5dc709e3dd84801d96bedb7a3d49a254d4ed1b452db15c761 +size 2776288736 diff --git a/granite-3.0-3b-a800m-instruct.Q8_0.gguf b/granite-3.0-3b-a800m-instruct.Q8_0.gguf new file mode 100644 index 0000000..db5bb53 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbcbc76edd5617881abe4a490146d89f3f9f462c87b6c424a67516a41052ba9 +size 3593000544 diff --git a/granite-3.0-3b-a800m-instruct.f16.gguf b/granite-3.0-3b-a800m-instruct.f16.gguf new file mode 100644 index 0000000..0aae080 --- /dev/null +++ b/granite-3.0-3b-a800m-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5aa4d5609fcf10b41551357a77c63909015b70e35bfc6336a82ae9f5c7159d +size 6754465824