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
2026-06-17 16:21:17 +08:00
commit 5678d8cb86
31 changed files with 334 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ 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 <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b8970">b8970</a> 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
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+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 (./)
+
+</details>
+
+## 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.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| 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
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+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.
+
+</details>
+
+## 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
--- a/ibm-granite_granite-4.1-30b-IQ2_M.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ2_S.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ2_XS.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ2_XXS.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ3_M.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ3_XS.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ3_XXS.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ4_NL.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-IQ4_XS.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q2_K.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q2_K_L.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q3_K_L.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q3_K_M.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q3_K_S.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q3_K_XL.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q4_0.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q4_1.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q4_K_L.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q4_K_M.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q4_K_S.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q5_K_L.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q5_K_M.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q5_K_S.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q6_K.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q6_K_L.gguf
+++ 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
--- a/ibm-granite_granite-4.1-30b-Q8_0.gguf
+++ 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
--- 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
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe3bb91e5970c2ddbfe2955865f7b64711a14f5e107998bffad6733f266243f9
+size 39951580032
--- 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
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f039329e147134a897fcf0aab828263e2ddd575dc0d6bf778c5a706837eb81
+size 17784515200
--- a/ibm-granite_granite-4.1-30b-imatrix.gguf
+++ 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