commit 5678d8cb863327051ac7574bfcf460698c2da058 Author: ModelHub XC Date: Wed Jun 17 16:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ibm-granite_granite-4.1-30b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81f226c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.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 +ibm-granite_granite-4.1-30b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.1-30b-imatrix.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b2d38f2 --- /dev/null +++ b/README.md @@ -0,0 +1,183 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: ibm-granite/granite-4.1-30b +license: apache-2.0 +tags: +- language +- granite-4.0 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of granite-4.1-30b by ibm-granite + +Using llama.cpp release b8970 for quantization. + +Original model: https://huggingface.co/ibm-granite/granite-4.1-30b + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d) + +Run them in your choice of tools: + +- [llama.cpp](https://github.com/ggml-org/llama.cpp) +- [ramalama](https://github.com/containers/ramalama) +- [LM Studio](https://lmstudio.ai/) +- [koboldcpp](https://github.com/LostRuins/koboldcpp) +- [Jan AI](https://www.jan.ai/) +- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) +- [LoLLMs](https://github.com/ParisNeo/lollms) + +Note: if it's a newly supported model, you may need to wait for an update from the developers. + +## Prompt format + +``` +<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|> +<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [granite-4.1-30b-bf16.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/tree/main/ibm-granite_granite-4.1-30b-bf16) | bf16 | 57.74GB | true | Full BF16 weights. | +| [granite-4.1-30b-Q8_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q8_0.gguf) | Q8_0 | 30.67GB | false | Extremely high quality, generally unneeded but max available quant. | +| [granite-4.1-30b-Q6_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q6_K_L.gguf) | Q6_K_L | 24.27GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [granite-4.1-30b-Q6_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q6_K.gguf) | Q6_K | 24.17GB | false | Very high quality, near perfect, *recommended*. | +| [granite-4.1-30b-Q5_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q5_K_L.gguf) | Q5_K_L | 20.84GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [granite-4.1-30b-Q5_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q5_K_M.gguf) | Q5_K_M | 20.74GB | false | High quality, *recommended*. | +| [granite-4.1-30b-Q5_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q5_K_S.gguf) | Q5_K_S | 19.98GB | false | High quality, *recommended*. | +| [granite-4.1-30b-Q4_1.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q4_1.gguf) | Q4_1 | 18.23GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [granite-4.1-30b-Q4_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q4_K_L.gguf) | Q4_K_L | 17.90GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [granite-4.1-30b-Q4_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q4_K_M.gguf) | Q4_K_M | 17.80GB | false | Good quality, default size for most use cases, *recommended*. | +| [granite-4.1-30b-Q4_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q4_K_S.gguf) | Q4_K_S | 16.64GB | false | Slightly lower quality with more space savings, *recommended*. | +| [granite-4.1-30b-IQ4_NL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ4_NL.gguf) | IQ4_NL | 16.56GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [granite-4.1-30b-Q4_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q4_0.gguf) | Q4_0 | 16.55GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [granite-4.1-30b-IQ4_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ4_XS.gguf) | IQ4_XS | 15.69GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [granite-4.1-30b-Q3_K_XL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q3_K_XL.gguf) | Q3_K_XL | 15.30GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [granite-4.1-30b-Q3_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q3_K_L.gguf) | Q3_K_L | 15.21GB | false | Lower quality but usable, good for low RAM availability. | +| [granite-4.1-30b-Q3_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q3_K_M.gguf) | Q3_K_M | 14.18GB | false | Low quality. | +| [granite-4.1-30b-IQ3_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ3_M.gguf) | IQ3_M | 13.13GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [granite-4.1-30b-Q3_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q3_K_S.gguf) | Q3_K_S | 12.78GB | false | Low quality, not recommended. | +| [granite-4.1-30b-IQ3_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ3_XS.gguf) | IQ3_XS | 12.21GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [granite-4.1-30b-IQ3_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ3_XXS.gguf) | IQ3_XXS | 11.51GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [granite-4.1-30b-Q2_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q2_K_L.gguf) | Q2_K_L | 11.09GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [granite-4.1-30b-Q2_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-Q2_K.gguf) | Q2_K | 10.99GB | false | Very low quality but surprisingly usable. | +| [granite-4.1-30b-IQ2_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ2_M.gguf) | IQ2_M | 10.65GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [granite-4.1-30b-IQ2_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ2_S.gguf) | IQ2_S | 9.94GB | false | Low quality, uses SOTA techniques to be usable. | +| [granite-4.1-30b-IQ2_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ2_XS.gguf) | IQ2_XS | 9.63GB | false | Low quality, uses SOTA techniques to be usable. | +| [granite-4.1-30b-IQ2_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.1-30b-GGUF/blob/main/ibm-granite_granite-4.1-30b-IQ2_XXS.gguf) | IQ2_XXS | 8.89GB | false | Very low quality, uses SOTA techniques to be usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/ibm-granite_granite-4.1-30b-GGUF --include "ibm-granite_granite-4.1-30b-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/ibm-granite_granite-4.1-30b-GGUF --include "ibm-granite_granite-4.1-30b-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ibm-granite_granite-4.1-30b-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/ibm-granite_granite-4.1-30b-IQ2_M.gguf b/ibm-granite_granite-4.1-30b-IQ2_M.gguf new file mode 100644 index 0000000..592f135 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69686725ca5e94062ac7bb1f2537d89e162e81f833d0d2c73bd6582f6bebec18 +size 10649265728 diff --git a/ibm-granite_granite-4.1-30b-IQ2_S.gguf b/ibm-granite_granite-4.1-30b-IQ2_S.gguf new file mode 100644 index 0000000..c784dea --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61984189ddcea05069e9d0a6b56208b99768e8262ef71d84df21ab0845a0bac +size 9944622656 diff --git a/ibm-granite_granite-4.1-30b-IQ2_XS.gguf b/ibm-granite_granite-4.1-30b-IQ2_XS.gguf new file mode 100644 index 0000000..8c952c2 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca439a729e1564f7041a241925b07984c2d6cd5443c20552b423940e0fb9f71 +size 9630049856 diff --git a/ibm-granite_granite-4.1-30b-IQ2_XXS.gguf b/ibm-granite_granite-4.1-30b-IQ2_XXS.gguf new file mode 100644 index 0000000..c13752e --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07d9c1a40702934525bb7ecc46f0f97882c72880a7da93a696fb6c8a519f5e9 +size 8891852352 diff --git a/ibm-granite_granite-4.1-30b-IQ3_M.gguf b/ibm-granite_granite-4.1-30b-IQ3_M.gguf new file mode 100644 index 0000000..d3b2335 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4b31967cc404fd6299b7f8e59057b73a54e6d027183a9e7cf00228614e6a68 +size 13133407808 diff --git a/ibm-granite_granite-4.1-30b-IQ3_XS.gguf b/ibm-granite_granite-4.1-30b-IQ3_XS.gguf new file mode 100644 index 0000000..861ac42 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78972383e43c50981443e8b03625cc16d1d78a11ded40afe07c92f02ef9211e9 +size 12210660928 diff --git a/ibm-granite_granite-4.1-30b-IQ3_XXS.gguf b/ibm-granite_granite-4.1-30b-IQ3_XXS.gguf new file mode 100644 index 0000000..b6c0057 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c695514fc3522c562c9c00fe4caf8d35dd18418d268ae0e11fc6ffa601fe2356 +size 11514340928 diff --git a/ibm-granite_granite-4.1-30b-IQ4_NL.gguf b/ibm-granite_granite-4.1-30b-IQ4_NL.gguf new file mode 100644 index 0000000..6e72059 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3227a2da0cd4852a123ffb3aec122f061e6be3241fc17907b890c0ab36d77b0f +size 16555959872 diff --git a/ibm-granite_granite-4.1-30b-IQ4_XS.gguf b/ibm-granite_granite-4.1-30b-IQ4_XS.gguf new file mode 100644 index 0000000..46f7f20 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:831510e6e2eeea3979c041b949d48a4f12f57e8dff7dc4ac52563cae42680e65 +size 15691933248 diff --git a/ibm-granite_granite-4.1-30b-Q2_K.gguf b/ibm-granite_granite-4.1-30b-Q2_K.gguf new file mode 100644 index 0000000..1b77e83 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd62c9a3c3ba4323e35dc066ad6cb8c2078fb85aa8a5ddfccbc807859de699c +size 10988021312 diff --git a/ibm-granite_granite-4.1-30b-Q2_K_L.gguf b/ibm-granite_granite-4.1-30b-Q2_K_L.gguf new file mode 100644 index 0000000..7d6e1bd --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5ad6a1059c85447e94a41f6971e4042fd50d46ecb7807cb75f368d1698e5dc +size 11087570496 diff --git a/ibm-granite_granite-4.1-30b-Q3_K_L.gguf b/ibm-granite_granite-4.1-30b-Q3_K_L.gguf new file mode 100644 index 0000000..940ce9f --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4970ddbc8a4bb86da38f403271fa37358989511236d3c909beb387f9e18ac194 +size 15205393984 diff --git a/ibm-granite_granite-4.1-30b-Q3_K_M.gguf b/ibm-granite_granite-4.1-30b-Q3_K_M.gguf new file mode 100644 index 0000000..5cbaf2e --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e9a47a3205062c79dbde5a6a556151f650075d0502b5e5ab02486fb11d2542 +size 14181983808 diff --git a/ibm-granite_granite-4.1-30b-Q3_K_S.gguf b/ibm-granite_granite-4.1-30b-Q3_K_S.gguf new file mode 100644 index 0000000..4ee0f00 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f809d3d092afd3d332ee7a912b0bfc3b30aaf723487432ec695dc3a1fde156fb +size 12778989120 diff --git a/ibm-granite_granite-4.1-30b-Q3_K_XL.gguf b/ibm-granite_granite-4.1-30b-Q3_K_XL.gguf new file mode 100644 index 0000000..620c521 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57295ac6a82ed990de0346db23eb409c8069b4096e4de0a41bb0b6703b6fd2d6 +size 15304943168 diff --git a/ibm-granite_granite-4.1-30b-Q4_0.gguf b/ibm-granite_granite-4.1-30b-Q4_0.gguf new file mode 100644 index 0000000..072469b --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69298b079c17c9417758e1b950c320fd98cde42a32711e76703a8f87faff42e9 +size 16553862720 diff --git a/ibm-granite_granite-4.1-30b-Q4_1.gguf b/ibm-granite_granite-4.1-30b-Q4_1.gguf new file mode 100644 index 0000000..2aa298a --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb31aa1bac7d945485463d688ac8593a3ad0e387a2e2c617221befbb51892c8 +size 18231584320 diff --git a/ibm-granite_granite-4.1-30b-Q4_K_L.gguf b/ibm-granite_granite-4.1-30b-Q4_K_L.gguf new file mode 100644 index 0000000..1e1aaa7 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7160fc88fc9d73c076c041be95e8ad26972f4e5b0219a5ecd7fbc3f53449311 +size 17895974464 diff --git a/ibm-granite_granite-4.1-30b-Q4_K_M.gguf b/ibm-granite_granite-4.1-30b-Q4_K_M.gguf new file mode 100644 index 0000000..1253fc7 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fdab47bedaf3c6d42d28c613474b44f54ec2d71bedab18d26b6782e180e1d15 +size 17796425280 diff --git a/ibm-granite_granite-4.1-30b-Q4_K_S.gguf b/ibm-granite_granite-4.1-30b-Q4_K_S.gguf new file mode 100644 index 0000000..3523e8e --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3669bf38619fdeceee4ea0d83036ed75b1a6cc15d20e64d2abe171390dc204 +size 16637748800 diff --git a/ibm-granite_granite-4.1-30b-Q5_K_L.gguf b/ibm-granite_granite-4.1-30b-Q5_K_L.gguf new file mode 100644 index 0000000..2bef857 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:855c27d964020651ba30dc1e83e866f08db286b42a863cfc096cfe52a75f3497 +size 20842473024 diff --git a/ibm-granite_granite-4.1-30b-Q5_K_M.gguf b/ibm-granite_granite-4.1-30b-Q5_K_M.gguf new file mode 100644 index 0000000..1dd7eab --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10969bc8c2baad84f8ee987af1367ac9fc0b2b14d32d90468377a9821e54b37 +size 20742923840 diff --git a/ibm-granite_granite-4.1-30b-Q5_K_S.gguf b/ibm-granite_granite-4.1-30b-Q5_K_S.gguf new file mode 100644 index 0000000..1e72631 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45a3ce3c65b9ea7a2c4edc04c2022f41b7dee2c8a4f64622210943ea11be251 +size 19976414784 diff --git a/ibm-granite_granite-4.1-30b-Q6_K.gguf b/ibm-granite_granite-4.1-30b-Q6_K.gguf new file mode 100644 index 0000000..814828b --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5248117c340421b28b155b2b3de8db8451472ad6fdc3e47ab2e5a34012377e25 +size 24171767360 diff --git a/ibm-granite_granite-4.1-30b-Q6_K_L.gguf b/ibm-granite_granite-4.1-30b-Q6_K_L.gguf new file mode 100644 index 0000000..57af916 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edddd52db58a344921bb3d3b75e45ff9dee58aa259c1964721907410d1636ae +size 24271316544 diff --git a/ibm-granite_granite-4.1-30b-Q8_0.gguf b/ibm-granite_granite-4.1-30b-Q8_0.gguf new file mode 100644 index 0000000..8cd85da --- /dev/null +++ b/ibm-granite_granite-4.1-30b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df79a90c7f567ddb9153d16d4945211f50ecdfc3323701584d210af42126414 +size 30674970176 diff --git a/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00001-of-00002.gguf b/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00001-of-00002.gguf new file mode 100644 index 0000000..b7ef915 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3bb91e5970c2ddbfe2955865f7b64711a14f5e107998bffad6733f266243f9 +size 39951580032 diff --git a/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00002-of-00002.gguf b/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00002-of-00002.gguf new file mode 100644 index 0000000..89c2810 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-bf16/ibm-granite_granite-4.1-30b-bf16-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f039329e147134a897fcf0aab828263e2ddd575dc0d6bf778c5a706837eb81 +size 17784515200 diff --git a/ibm-granite_granite-4.1-30b-imatrix.gguf b/ibm-granite_granite-4.1-30b-imatrix.gguf new file mode 100644 index 0000000..b36b622 --- /dev/null +++ b/ibm-granite_granite-4.1-30b-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3b6dd14dd76521871872b265121a4674abcbcc1456422db39450ddc8c45253 +size 14748960